From 22bbe3f1023a68a7d1f2de566dd4242fdcfd36c3 Mon Sep 17 00:00:00 2001 From: Sheral Kumar Date: Fri, 25 Sep 2026 14:27:53 -0400 Subject: [PATCH] [ROCm][CI] Expand single-GPU coverage on MI355 DPX (#57599) Signed-off-by: Sheral Kumar Signed-off-by: Andreas Karatzas Signed-off-by: Andreas Karatzas Signed-off-by: Andreas Karatzas Co-authored-by: Andreas Karatzas Co-authored-by: Codex Co-authored-by: Andreas Karatzas Co-authored-by: OpenAI Codex Co-authored-by: Andreas Karatzas --- .buildkite/test-amd.yaml | 1852 ++++++++--------- .buildkite/test_areas/basic_correctness.yaml | 4 +- .buildkite/test_areas/benchmarks.yaml | 4 +- .buildkite/test_areas/compile.yaml | 8 +- .buildkite/test_areas/cuda.yaml | 4 +- .buildkite/test_areas/disaggregated.yaml | 2 +- .buildkite/test_areas/distributed.yaml | 6 +- .buildkite/test_areas/e2e_integration.yaml | 4 +- .buildkite/test_areas/engine.yaml | 8 +- .buildkite/test_areas/entrypoints.yaml | 44 +- .buildkite/test_areas/expert_parallelism.yaml | 4 +- .buildkite/test_areas/kernels.yaml | 84 +- .buildkite/test_areas/lm_eval.yaml | 30 +- .buildkite/test_areas/lora.yaml | 4 +- .buildkite/test_areas/misc.yaml | 48 +- .buildkite/test_areas/models_basic.yaml | 20 +- .buildkite/test_areas/models_language.yaml | 20 +- .buildkite/test_areas/models_multimodal.yaml | 28 +- .buildkite/test_areas/plugins.yaml | 4 +- .buildkite/test_areas/pytorch.yaml | 12 +- .buildkite/test_areas/quantization.yaml | 8 +- .buildkite/test_areas/ray_compat.yaml | 4 +- .buildkite/test_areas/rust_frontend.yaml | 16 +- .buildkite/test_areas/samplers.yaml | 4 +- .buildkite/test_areas/spec_decode.yaml | 20 +- 25 files changed, 1162 insertions(+), 1080 deletions(-) diff --git a/.buildkite/test-amd.yaml b/.buildkite/test-amd.yaml index 825e9968bb..9ef6cbcdde 100644 --- a/.buildkite/test-amd.yaml +++ b/.buildkite/test-amd.yaml @@ -538,25 +538,6 @@ steps: #----------------------------------------------------- mi300 · basic_correctness -----------------------------------------------------# -- label: ":amd: (MI300) Basic Correctness" # TBD - timeout_in_minutes: 60 - mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] - dind: false - agent_pool: mi300_1 - fast_check: true - working_dir: "/vllm-workspace/tests" - source_file_dependencies: - - vllm/ - - tests/basic_correctness/test_basic_correctness - - tests/basic_correctness/test_cpu_offload - - tests/basic_correctness/test_mem.py - optional: true - commands: - - export VLLM_WORKER_MULTIPROC_METHOD=spawn - - pytest -v -s basic_correctness/test_mem.py - - VLLM_TARGET_TEST_SUITE=MI300 pytest -v -s basic_correctness/test_basic_correctness.py - - pytest -v -s basic_correctness/test_cpu_offload.py - - label: ":amd: (MI300) Distributed Models Shard %N" timeout_in_minutes: 80 parallelism: 3 @@ -589,22 +570,6 @@ steps: commands: - case "$$BUILDKITE_PARALLEL_JOB" in 0) TARGET_TEST_SUITE=MI300 pytest basic_correctness/ -v -s -m 'distributed(num_gpus=2)' && HIP_VISIBLE_DEVICES=0,1 pytest -v -s model_executor/model_loader/test_sharded_state_loader.py -m '(not slow_test)' ;; 1) pytest models/transformers/test_backend.py -v -s -m 'distributed(num_gpus=2)' && pytest models/language -v -s -m 'distributed(num_gpus=2)' && VLLM_ROCM_USE_AITER=1 pytest -v -s models/test_hyv4_rocm.py -m 'distributed(num_gpus=2)' ;; 2) pytest models/multimodal -v -s -m 'distributed(num_gpus=2)' --ignore models/multimodal/generation/test_whisper.py --ignore models/multimodal/generation/test_phi4siglip.py && pytest models/multimodal/generation/test_phi4siglip.py -v -s -m 'distributed(num_gpus=2)' && VLLM_WORKER_MULTIPROC_METHOD=spawn pytest models/multimodal/generation/test_whisper.py -v -s -m 'distributed(num_gpus=2)' && pytest -v -s models/test_vision.py -m 'distributed(num_gpus=2)' ;; *) exit 2 ;; esac -#-------------------------------------------------------- mi300 · benchmarks ---------------------------------------------------------# - -- label: ":amd: (MI300) Benchmarks CLI" # TBD - timeout_in_minutes: 40 - mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] - dind: false - agent_pool: mi300_1 - optional: true - working_dir: "/vllm-workspace/tests" - source_file_dependencies: - - vllm/ - - tests/benchmarks/ - - rust/src/bench/tests/python_serve_flags.txt - commands: - - pytest -v -s benchmarks/ - #---------------------------------------------------------- mi300 · compile ----------------------------------------------------------# - label: ":amd: (MI300) PyTorch Compilation" # TBD @@ -922,22 +887,6 @@ steps: - pytest -v -s distributed/test_shm_buffer.py - pytest -v -s distributed/test_shm_storage.py -- label: ":amd: (MI300) EPLB Algorithm" # TBD - timeout_in_minutes: 30 - mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] - dind: false - agent_pool: mi300_1 - optional: true - working_dir: "/vllm-workspace/tests" - source_file_dependencies: - - vllm/distributed/eplb - - tests/distributed/test_eplb_algo.py - - tests/distributed/test_eplb_utils.py - - vllm/platforms/rocm.py - commands: - - pytest -v -s distributed/test_eplb_algo.py - - pytest -v -s distributed/test_eplb_utils.py - - label: ":amd: (MI300) EPLB Execution" # TBD timeout_in_minutes: 35 mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] @@ -1024,7 +973,7 @@ steps: - pytest -v -s models/test_vision.py -m 'distributed(num_gpus=4)' - label: ":amd: (MI300) Distributed Torchrun + Examples" # TBD - timeout_in_minutes: 35 + timeout_in_minutes: 55 mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] dind: false agent_pool: mi300_4 @@ -1155,38 +1104,6 @@ steps: - pytest -v -s distributed/test_symm_mem_allreduce.py - pytest -v -s distributed/test_multiproc_executor.py::test_multiproc_executor_multi_node -#---------------------------------------------------------- mi300 · engine -----------------------------------------------------------# - -- label: ":amd: (MI300) Engine Core" # TBD - timeout_in_minutes: 40 - mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] - dind: false - agent_pool: mi300_1 - optional: true - working_dir: "/vllm-workspace/tests" - source_file_dependencies: - - vllm/ - - tests/engine - - tests/test_sequence - - tests/test_config - - tests/test_logger - - tests/test_vllm_port - - tests/jit_monitor/test_hooks.py - - tests/jit_monitor/test_hooks_gpu.py - - vllm/compilation/ - - vllm/config/ - - vllm/engine/ - - vllm/entrypoints/logger.py - - vllm/envs.py - - vllm/logger.py - - vllm/logging_utils/ - - vllm/platforms/ - - vllm/sequence.py - - vllm/triton_utils/ - - vllm/utils/ - commands: - - pytest -v -s engine test_sequence.py test_config.py test_logger.py test_vllm_port.py jit_monitor/test_hooks.py jit_monitor/test_hooks_gpu.py - #-------------------------------------------------------- mi300 · entrypoints --------------------------------------------------------# - label: ":amd: (MI300) Entrypoints Unit" # TBD @@ -1208,95 +1125,6 @@ steps: - pytest -v -s entrypoints/weight_transfer - pytest -v -s entrypoints/launchers -- label: ":amd: (MI300) Entrypoints Integration (LLM)" # TBD - timeout_in_minutes: 90 - mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] - dind: false - agent_pool: mi300_1 - optional: true - fast_check: true - working_dir: "/vllm-workspace/tests" - source_file_dependencies: - - vllm/ - - tests/entrypoints/llm - commands: - - export VLLM_WORKER_MULTIPROC_METHOD=spawn - - pytest -v -s entrypoints/llm --ignore=entrypoints/llm/test_generate.py --ignore=entrypoints/llm/test_collective_rpc.py --ignore=entrypoints/llm/offline_mode - - pytest -v -s entrypoints/llm/test_generate.py # it needs a clean process - - pytest -v -s entrypoints/llm/offline_mode # Needs to avoid interference with other tests - -- label: ":amd: (MI300) Entrypoints Integration (API Server) %N" - timeout_in_minutes: 65 - parallelism: 4 - mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] - dind: false - agent_pool: mi300_1 - optional: true - fast_check: true - working_dir: "/vllm-workspace/tests" - source_file_dependencies: - - vllm/ - - tests/entrypoints/serve - - tests/entrypoints/scale_out - commands: - - export VLLM_WORKER_MULTIPROC_METHOD=spawn - - pytest -v -s entrypoints/serve --ignore=entrypoints/serve/dev/rpc --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB - - if [ "$$BUILDKITE_PARALLEL_JOB" = "1" ]; then PYTHONPATH=/vllm-workspace pytest -v -s entrypoints/serve/dev/rpc; fi - - pytest -v -s entrypoints/scale_out --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB - -- label: ":amd: (MI300) Entrypoints Integration (OpenAI API completion)" # TBD - timeout_in_minutes: 65 - mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] - dind: false - agent_pool: mi300_1 - fast_check: true - optional: true - working_dir: "/vllm-workspace/tests" - source_file_dependencies: - - vllm/ - - tests/entrypoints/openai - commands: - - export VLLM_WORKER_MULTIPROC_METHOD=spawn - - pytest -v -s entrypoints/openai/completion --ignore=entrypoints/openai/completion/test_tensorizer_entrypoint.py - - pytest -v -s entrypoints/openai --ignore=entrypoints/openai/completion --ignore=entrypoints/openai/chat_completion --ignore=entrypoints/openai/responses --ignore=entrypoints/openai/correctness - -- label: ":amd: (MI300) Entrypoints Integration (OpenAI API chat_completion)" # TBD - timeout_in_minutes: 70 - mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] - dind: false - agent_pool: mi300_1 - fast_check: true - optional: true - working_dir: "/vllm-workspace/tests" - source_file_dependencies: - - vllm/ - - tests/entrypoints/openai - commands: - - export VLLM_WORKER_MULTIPROC_METHOD=spawn - - pytest -v -s entrypoints/openai/chat_completion - -- label: ":amd: (MI300) Entrypoints Integration (API Server Generate)" # TBD - timeout_in_minutes: 65 - mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] - dind: false - agent_pool: mi300_1 - optional: true - fast_check: true - working_dir: "/vllm-workspace/tests" - source_file_dependencies: - - vllm/ - - tests/tool_use - - tests/entrypoints/tool_parsers - - tests/entrypoints/anthropic - - tests/entrypoints/cohere - - tests/entrypoints/generate - commands: - - pytest -v -s tool_use - - pytest -v -s entrypoints/tool_parsers - - pytest -v -s entrypoints/generate - - pytest -v -s entrypoints/anthropic - - pytest -v -s entrypoints/cohere - - label: ":amd: (MI300) Entrypoints Integration (Responses API)" # TBD timeout_in_minutes: 50 mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] @@ -1341,26 +1169,6 @@ steps: - export VLLM_WORKER_MULTIPROC_METHOD=spawn - pytest -v -s entrypoints/multimodal -- label: ":amd: (MI300) OpenAI API Correctness" # TBD - timeout_in_minutes: 30 - mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] - dind: false - agent_pool: mi300_1 - optional: true - working_dir: "/vllm-workspace/tests" - source_file_dependencies: - - csrc/ - - vllm/entrypoints/openai/ - - vllm/model_executor/layers/ - - vllm/v1/attention/backends/ - - vllm/v1/attention/selector.py - - vllm/_aiter_ops.py - - vllm/platforms/rocm.py - - vllm/model_executor/model_loader/ - commands: - - bash ../tools/install_torchcodec_rocm.sh || exit 1 - - pytest -s entrypoints/openai/correctness/ - - label: ":amd: (MI300) Scale-out EC Connector E2E" timeout_in_minutes: 60 mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] @@ -1380,6 +1188,25 @@ steps: #----------------------------------------------------------- mi300 · evals -----------------------------------------------------------# +- label: ":amd: (MI300) LM Eval Small Models" # TBD + timeout_in_minutes: 45 + mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] + dind: false + agent_pool: mi300_1 + working_dir: "/vllm-workspace/tests" + source_file_dependencies: + - csrc/ + - vllm/model_executor/layers/quantization + - vllm/model_executor/models/ + - vllm/model_executor/model_loader/ + - vllm/v1/attention/backends/ + - vllm/v1/attention/selector.py + - vllm/_aiter_ops.py + - vllm/platforms/rocm.py + optional: true + commands: + - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-small.txt + - label: ":amd: (MI300) DeepSeek V2-Lite Prefetch Offload Accuracy" # TBD timeout_in_minutes: 30 mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] @@ -1402,25 +1229,6 @@ steps: commands: - bash .buildkite/scripts/scheduled_integration_test/deepseek_v2_lite_prefetch_offload.sh 0.25 200 8030 -- label: ":amd: (MI300) LM Eval Small Models" # TBD - timeout_in_minutes: 45 - mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] - dind: false - agent_pool: mi300_1 - working_dir: "/vllm-workspace/tests" - source_file_dependencies: - - csrc/ - - vllm/model_executor/layers/quantization - - vllm/model_executor/models/ - - vllm/model_executor/model_loader/ - - vllm/v1/attention/backends/ - - vllm/v1/attention/selector.py - - vllm/_aiter_ops.py - - vllm/platforms/rocm.py - optional: true - commands: - - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-small.txt - - label: ":amd: (MI300) MRCR Eval Small Models" # TBD timeout_in_minutes: 40 mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] @@ -1459,22 +1267,6 @@ steps: commands: - pytest -s -v test_lm_eval_correctness.py --config-list-file=configs/models-small-rocm.txt -- label: ":amd: (MI300) Multimodal Accuracy Eval (Small Models)" # TBD - timeout_in_minutes: 35 - mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] - dind: false - agent_pool: mi300_1 - optional: true - working_dir: "/vllm-workspace/.buildkite/lm-eval-harness" - source_file_dependencies: - - vllm/multimodal/ - - vllm/inputs/ - - vllm/v1/core/ - - vllm/platforms/rocm.py - - vllm/model_executor/model_loader/ - commands: - - pytest -s -v test_lm_eval_correctness.py --config-list-file=configs/models-mm-small.txt --tp-size=1 - - label: ":amd: (MI300) GPQA Eval (GPT-OSS)" # TBD timeout_in_minutes: 40 mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] @@ -1697,44 +1489,84 @@ steps: - export VLLM_USE_DEEP_GEMM=0 - pytest -s -v test_lm_eval_correctness.py --config-list-file=configs/models-large-rocm-tp4.txt --tp-size=4 -#--------------------------------------------------------- mi300 · examples ----------------------------------------------------------# +#---------------------------------------------------------- mi300 · kernels ----------------------------------------------------------# -- label: ":amd: (MI300) Examples" # TBD - timeout_in_minutes: 75 +- label: ":amd: (MI300) Core Operation Kernels Shard %N" # TBD + timeout_in_minutes: 40 + mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] + dind: false + agent_pool: mi300_1 + parallelism: 3 + working_dir: "/vllm-workspace/tests" + source_file_dependencies: + - csrc/ + - tests/kernels/core + - tests/kernels/test_top_k_per_row.py + - tests/kernels/test_concat_mla_q.py + - tests/kernels/test_rocm_fp32_router_gemm.py + - vllm/model_executor/layers/fused_moe/router/gate_linear.py + - vllm/model_executor/layers/fused_moe/router/rocm_fp32_router_gemm.py + - vllm/model_executor/layers/rotary_embedding/ + - vllm/_aiter_ops.py + - vllm/platforms/rocm.py + - tests/kernels/test_fused_qk_norm_rope_gate.py + optional: true + commands: + - pytest -v -s kernels/core --ignore=kernels/core/test_minimax_reduce_rms.py kernels/test_fused_qk_norm_rope_gate.py kernels/test_concat_mla_q.py kernels/test_top_k_per_row.py kernels/test_rocm_fp32_router_gemm.py --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT + +- label: ":amd: (MI300) Quantization Kernels Shard %N" + timeout_in_minutes: 120 + parallelism: 6 mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] dind: false agent_pool: mi300_1 optional: true - working_dir: "/vllm-workspace/examples" + working_dir: "/vllm-workspace/tests" source_file_dependencies: - - vllm/entrypoints - - vllm/multimodal - - examples/ + - csrc/quantization/ + - csrc/rocm/ + - vllm/model_executor/layers/quantization + - tests/kernels/quantization + - tests/kernels/quant_utils.py + - tests/kernels/utils.py + - vllm/_aiter_ops.py + - vllm/kernels/aiter_ops.py + - vllm/_custom_ops.py + - vllm/envs.py + - vllm/platforms/rocm.py + - vllm/model_executor/kernels/ + - vllm/v1/attention/backends/rocm_aiter_fa.py + - vllm/config/ + - tests/kernels/quantization/test_rocm_skinny_gemms.py + commands: + - pytest -v -s kernels/quantization -k "not test_nvfp4_dense_emulation" --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT + +- label: ":amd: (MI300) MoE Kernels Shard %N" # TBD + timeout_in_minutes: 55 + mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] + dind: false + agent_pool: mi300_1 + optional: true + parallelism: 5 + working_dir: "/vllm-workspace/tests" + source_file_dependencies: + - csrc/quantization/cutlass_w8a8/moe/ + - csrc/moe/ + - csrc/rocm/ + - tests/kernels/moe + - tests/kernels/utils.py + - vllm/model_executor/layers/fused_moe/ + - vllm/model_executor/layers/quantization/mxfp4.py + - vllm/model_executor/layers/quantization/utils/quant_utils.py + - vllm/distributed/device_communicators/ + - vllm/envs.py + - vllm/config + - vllm/_aiter_ops.py - vllm/platforms/rocm.py commands: - # Basic - # Multi-modal models - # Pooling models - # Features demo - - pip install --no-deps tensorizer - - python3 basic/offline_inference/chat.py - - python3 basic/offline_inference/generate.py --model facebook/opt-125m - - python3 basic/offline_inference/generate.py --model meta-llama/Llama-2-13b-chat-hf --cpu-offload-gb 10 - - python3 basic/offline_inference/classify.py - - python3 basic/offline_inference/embed.py - - python3 basic/offline_inference/score.py - - python3 generate/multimodal/audio_language_offline.py --seed 0 - - python3 generate/multimodal/vision_language_offline.py --seed 0 - - python3 generate/multimodal/vision_language_multi_image_offline.py --seed 0 - - python3 generate/multimodal/encoder_decoder_multimodal_offline.py --model-type whisper --seed 0 - - python3 pooling/embed/vision_embedding_offline.py --seed 0 - - python3 features/automatic_prefix_caching/prefix_caching_offline.py - - python3 deployment/llm_engine_example.py - - python3 features/tensorize_vllm_model.py --model facebook/opt-125m serialize --serialized-directory /tmp/ --suffix v1 && python3 features/tensorize_vllm_model.py --model facebook/opt-125m deserialize --path-to-tensors /tmp/vllm/facebook/opt-125m/v1/model.tensors - - python3 features/speculative_decoding/spec_decode_offline.py --test --method eagle --num_spec_tokens 3 --dataset-name hf --dataset-path philschmid/mt-bench --num-prompts 80 --temp 0 --top-p 1.0 --top-k -1 --tp 1 --enable-chunked-prefill --max-model-len 2048 - - python3 features/speculative_decoding/spec_decode_offline.py --test --method eagle3 --num_spec_tokens 3 --dataset-name hf --dataset-path philschmid/mt-bench --num-prompts 80 --temp 0 --top-p 1.0 --top-k -1 --tp 1 --enable-chunked-prefill --max-model-len 1536 - -#---------------------------------------------------------- mi300 · kernels ----------------------------------------------------------# + - pytest -v -s kernels/moe --ignore=kernels/moe/test_modular_oai_triton_moe.py --ignore=kernels/moe/test_modular_kernel_combinations.py --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT + - pytest -v -s kernels/moe/test_modular_oai_triton_moe.py --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT + - VLLM_ROCM_USE_AITER=1 VLLM_ROCM_USE_AITER_MOE=1 pytest -v -s kernels/moe/test_modular_kernel_combinations.py --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT - label: ":amd: (MI300) vLLM IR" # TBD timeout_in_minutes: 50 @@ -1877,60 +1709,6 @@ steps: commands: - pytest -v -s kernels/mamba -- label: ":amd: (MI300) MoE Kernels Shard %N" # TBD - timeout_in_minutes: 55 - mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] - dind: false - agent_pool: mi300_1 - optional: true - parallelism: 5 - working_dir: "/vllm-workspace/tests" - source_file_dependencies: - - csrc/quantization/cutlass_w8a8/moe/ - - csrc/moe/ - - csrc/rocm/ - - tests/kernels/moe - - tests/kernels/utils.py - - vllm/model_executor/layers/fused_moe/ - - vllm/model_executor/layers/quantization/mxfp4.py - - vllm/model_executor/layers/quantization/utils/quant_utils.py - - vllm/distributed/device_communicators/ - - vllm/envs.py - - vllm/config - - vllm/_aiter_ops.py - - vllm/platforms/rocm.py - commands: - - pytest -v -s kernels/moe --ignore=kernels/moe/test_modular_oai_triton_moe.py --ignore=kernels/moe/test_modular_kernel_combinations.py --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT - - pytest -v -s kernels/moe/test_modular_oai_triton_moe.py --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT - - VLLM_ROCM_USE_AITER=1 VLLM_ROCM_USE_AITER_MOE=1 pytest -v -s kernels/moe/test_modular_kernel_combinations.py --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT - -- label: ":amd: (MI300) Quantization Kernels Shard %N" - timeout_in_minutes: 120 - parallelism: 6 - mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] - dind: false - agent_pool: mi300_1 - optional: true - working_dir: "/vllm-workspace/tests" - source_file_dependencies: - - csrc/quantization/ - - csrc/rocm/ - - vllm/model_executor/layers/quantization - - tests/kernels/quantization - - tests/kernels/quant_utils.py - - tests/kernels/utils.py - - vllm/_aiter_ops.py - - vllm/kernels/aiter_ops.py - - vllm/_custom_ops.py - - vllm/envs.py - - vllm/platforms/rocm.py - - vllm/model_executor/kernels/ - - vllm/v1/attention/backends/rocm_aiter_fa.py - - vllm/config/ - - tests/kernels/quantization/test_rocm_skinny_gemms.py - commands: - - pytest -v -s kernels/quantization -k "not test_nvfp4_dense_emulation" --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT - - label: ":amd: (MI300) DeepEP FP8 MoE Kernels" # TBD timeout_in_minutes: 55 mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] @@ -1952,21 +1730,6 @@ steps: #----------------------------------------------------------- mi300 · lora ------------------------------------------------------------# -- label: ":amd: (MI300) LoRA Shard %N" # TBD - timeout_in_minutes: 85 - mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] - dind: false - agent_pool: mi300_1 - parallelism: 4 - optional: true - working_dir: "/vllm-workspace/tests" - source_file_dependencies: - - vllm/lora - - tests/lora - - vllm/platforms/rocm.py - commands: - - pytest -v -s lora --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --ignore=lora/test_chatglm3_tp.py --ignore=lora/test_llama_tp.py --ignore=lora/test_qwen3_with_multi_loras.py --ignore=lora/test_olmoe_tp.py --ignore=lora/test_deepseekv2_tp.py --ignore=lora/test_gptoss_tp.py --ignore=lora/test_qwen3moe_tp.py --ignore=lora/test_qwen35_densemodel_lora.py - - label: ":amd: (MI300) LoRA TP (Distributed) %N" timeout_in_minutes: 65 parallelism: 4 @@ -2035,26 +1798,6 @@ steps: commands: - pytest -v -s models/test_initialization.py::test_can_initialize_small_subset -- label: ":amd: (MI300) Basic Models (Other)" # TBD - timeout_in_minutes: 65 - mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] - dind: false - agent_pool: mi300_1 - optional: true - working_dir: "/vllm-workspace/tests" - source_file_dependencies: - - vllm/ - - tests/models/test_terratorch.py - - tests/models/transformers/test_backend.py - - tests/models/test_registry.py - - tests/models/test_hyv4_rocm.py - - tests/models/test_vision.py - - tests/models/test_deepseek_v4_vl_rocm.py - commands: - - pytest -v -s models/test_terratorch.py models/transformers/test_backend.py models/test_registry.py models/test_deepseek_v4_vl_rocm.py - - VLLM_ROCM_USE_AITER=1 pytest -v -s models/test_hyv4_rocm.py -m 'not distributed' - - pytest -v -s models/test_vision.py::test_simple_mrope_vision_model_spatial_merge - #----------------------------------------------------- mi300 · models / language -----------------------------------------------------# - label: ":amd: (MI300) Language Models (MTEB)" # TBD @@ -2084,43 +1827,6 @@ steps: commands: - pytest -v -s models/language/pooling -m 'not core_model' --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB -- label: ":amd: (MI300) Language Models (Standard)" # TBD - timeout_in_minutes: 60 - mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] - dind: false - agent_pool: mi300_1 - optional: true - working_dir: "/vllm-workspace/tests" - source_file_dependencies: - - vllm/ - - tests/models/language - commands: - - pip freeze | grep -E 'torch' - - pytest -v -s models/language -m 'core_model and (not slow_test)' - -- label: ":amd: (MI300) Language Models (Extra Standard) Shard %N" # TBD - timeout_in_minutes: 40 - mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] - dind: false - agent_pool: mi300_1 - optional: true - parallelism: 2 - working_dir: "/vllm-workspace/tests" - source_file_dependencies: - - vllm/model_executor/models/ - - vllm/model_executor/model_loader/ - - vllm/model_executor/layers/ - - vllm/v1/attention/backends/ - - vllm/v1/attention/selector.py - - tests/models/language/pooling/test_embedding.py - - tests/models/language/generation/test_common.py - - tests/models/language/pooling/test_classification.py - - vllm/_aiter_ops.py - - vllm/platforms/rocm.py - commands: - - pip freeze | grep -E 'torch' - - pytest -v -s models/language -m 'core_model and slow_test' --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB - - label: ":amd: (MI300) Language Models (Extended Generation)" # TBD timeout_in_minutes: 95 mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] @@ -2181,20 +1887,6 @@ steps: commands: - pytest -v -s models/multimodal/generation/test_common.py -m 'split(group=1) and not core_model' -- label: ":amd: (MI300) Multimodal Models (Standard) 1: qwen2" # TBD - timeout_in_minutes: 65 - mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] - dind: false - agent_pool: mi300_1 - optional: true - working_dir: "/vllm-workspace/tests" - source_file_dependencies: - - vllm/ - - tests/models/multimodal - commands: - - pytest -v -s models/multimodal/generation/test_common.py -m core_model -k "qwen2" - - pytest -v -s models/multimodal/generation/test_ultravox.py -m core_model - - label: ":amd: (MI300) Multimodal Models (Standard) 3: llava + qwen2_vl" # TBD timeout_in_minutes: 55 mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] @@ -2239,21 +1931,6 @@ steps: commands: - pytest -v -s models/multimodal/pooling -m 'not core_model' -- label: ":amd: (MI300) Multimodal Models (Standard) 2: qwen3 + gemma" # TBD - timeout_in_minutes: 55 - mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] - dind: false - agent_pool: mi300_1 - optional: true - working_dir: "/vllm-workspace/tests" - source_file_dependencies: - - vllm/ - - tests/models/multimodal - commands: - - pytest -v -s models/multimodal/generation/test_common.py -m core_model -k "qwen3 or gemma" - - pytest -v -s models/multimodal/generation/test_mm_prefix_lm.py -m core_model - - pytest -v -s models/multimodal/generation/test_qwen2_5_vl.py -m core_model - #----------------------------------------------------- mi300 · models / quantized -----------------------------------------------------# - label: ":amd: (MI300) Quantized Models" # TBD @@ -2650,6 +2327,51 @@ steps: #------------------------------------------------------------ mi300 · v1 -------------------------------------------------------------# +- label: ":amd: (MI300) Spec Decode Speculators + MTP" # TBD + timeout_in_minutes: 75 + mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] + dind: false + agent_pool: mi300_1 + optional: true + working_dir: "/vllm-workspace/tests" + source_file_dependencies: + - vllm/v1/spec_decode/ + - vllm/v1/worker/gpu/spec_decode/ + - vllm/model_executor/model_loader/ + - vllm/v1/sample/ + - vllm/model_executor/layers/ + - vllm/transformers_utils/configs/speculators/ + - tests/v1/e2e/spec_decode/ + - vllm/platforms/rocm.py + - vllm/v1/attention/backends/ + commands: + - pytest -v -s v1/e2e/spec_decode/speculators/ + - pytest -v -s v1/e2e/spec_decode/mtp/ + +- label: ":amd: (MI300) V1 Spec Decode" # TBD + timeout_in_minutes: 50 + mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] + dind: false + agent_pool: mi300_1 + working_dir: "/vllm-workspace/tests" + source_file_dependencies: + - vllm/ + - tests/v1/spec_decode + - vllm/config/ + - vllm/distributed/ + - vllm/inputs/ + - vllm/model_executor/ + - vllm/models/qwen4_exp/ + - vllm/platforms/ + - vllm/sampling_params.py + - vllm/transformers_utils/ + - vllm/utils/ + - vllm/v1/ + optional: true + commands: + - export VLLM_WORKER_MULTIPROC_METHOD=spawn + - pytest -v -s -m 'not slow_test' v1/spec_decode + - label: ":amd: (MI300) Acceptance Length (Large Models)" # TBD timeout_in_minutes: 45 mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] @@ -2697,102 +2419,6 @@ steps: - pytest -v -s v1/engine --ignore v1/engine/test_preprocess_error_handling.py - pytest -v -s v1/test_tensor_ipc_queue.py -- label: ":amd: (MI300) Spec Decode Draft Model" # TBD - timeout_in_minutes: 60 - mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] - dind: false - agent_pool: mi300_1 - optional: true - working_dir: "/vllm-workspace/tests" - source_file_dependencies: - - vllm/v1/spec_decode/ - - vllm/v1/worker/gpu/spec_decode/ - - vllm/model_executor/model_loader/ - - vllm/v1/sample/ - - vllm/model_executor/layers/ - - tests/v1/e2e/spec_decode/ - - vllm/platforms/rocm.py - commands: - - pytest -v -s v1/e2e/spec_decode/draft_model/ - -- label: ":amd: (MI300) Spec Decode Eagle 1: DeepSeek + Qwen" - timeout_in_minutes: 60 - mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] - dind: false - agent_pool: mi300_1 - optional: true - working_dir: "/vllm-workspace/tests" - source_file_dependencies: - - vllm/v1/spec_decode/ - - vllm/v1/worker/gpu/spec_decode/ - - vllm/model_executor/model_loader/ - - vllm/v1/sample/ - - vllm/model_executor/layers/ - - tests/v1/e2e/spec_decode/ - - vllm/platforms/rocm.py - commands: - - pytest -v -s v1/e2e/spec_decode/eagle/ -k "deepseek_eagle or qwen3_eagle3" - -- label: ":amd: (MI300) Spec Decode Eagle 2: Llama 3 + Qwen VL + Other" - timeout_in_minutes: 60 - mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] - dind: false - agent_pool: mi300_1 - optional: true - working_dir: /vllm-workspace/tests - source_file_dependencies: - - vllm/v1/spec_decode/ - - vllm/v1/worker/gpu/spec_decode/ - - vllm/model_executor/model_loader/ - - vllm/v1/sample/ - - vllm/model_executor/layers/ - - tests/v1/e2e/spec_decode/ - - vllm/platforms/rocm.py - commands: - - pytest -v -s v1/e2e/spec_decode/eagle/ -k "not deepseek_eagle and not qwen3_eagle3" - - -- label: ":amd: (MI300) Spec Decode N-Gram + Suffix" # TBD - timeout_in_minutes: 35 - mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] - dind: false - agent_pool: mi300_1 - optional: true - working_dir: "/vllm-workspace/tests" - source_file_dependencies: - - vllm/v1/spec_decode/ - - vllm/v1/worker/gpu/spec_decode/ - - vllm/model_executor/model_loader/ - - vllm/v1/sample/ - - vllm/model_executor/layers/ - - tests/v1/e2e/spec_decode/ - - tests/spec_decode/ - - vllm/platforms/rocm.py - commands: - - pytest -v -s v1/e2e/spec_decode/ngram_suffix/ - - python3 spec_decode/test_custom_proposer.py - -- label: ":amd: (MI300) Spec Decode Speculators + MTP" # TBD - timeout_in_minutes: 75 - mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] - dind: false - agent_pool: mi300_1 - optional: true - working_dir: "/vllm-workspace/tests" - source_file_dependencies: - - vllm/v1/spec_decode/ - - vllm/v1/worker/gpu/spec_decode/ - - vllm/model_executor/model_loader/ - - vllm/v1/sample/ - - vllm/model_executor/layers/ - - vllm/transformers_utils/configs/speculators/ - - tests/v1/e2e/spec_decode/ - - vllm/platforms/rocm.py - - vllm/v1/attention/backends/ - commands: - - pytest -v -s v1/e2e/spec_decode/speculators/ - - pytest -v -s v1/e2e/spec_decode/mtp/ - - label: ":amd: (MI300) Speculators Correctness Nightly" timeout_in_minutes: 40 mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] @@ -2826,30 +2452,6 @@ steps: - export VLLM_ALLOW_INSECURE_SERIALIZATION=1 - pytest -v -s v1/spec_decode/test_speculators_correctness.py -m slow_test -- label: ":amd: (MI300) V1 Spec Decode" # TBD - timeout_in_minutes: 50 - mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] - dind: false - agent_pool: mi300_1 - working_dir: "/vllm-workspace/tests" - source_file_dependencies: - - vllm/ - - tests/v1/spec_decode - - vllm/config/ - - vllm/distributed/ - - vllm/inputs/ - - vllm/model_executor/ - - vllm/models/qwen4_exp/ - - vllm/platforms/ - - vllm/sampling_params.py - - vllm/transformers_utils/ - - vllm/utils/ - - vllm/v1/ - optional: true - commands: - - export VLLM_WORKER_MULTIPROC_METHOD=spawn - - pytest -v -s -m 'not slow_test' v1/spec_decode - - label: ":amd: (MI300) Extract Hidden States Integration" # TBD timeout_in_minutes: 30 mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] @@ -2904,283 +2506,6 @@ steps: commands: - pytest -v -s v1/attention --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT -- label: ":amd: (MI300) V1 Core" - timeout_in_minutes: 60 - mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] - dind: false - agent_pool: mi300_1 - working_dir: "/vllm-workspace/tests" - source_file_dependencies: - - vllm/ - - tests/v1/core - - tests/v1/executor - - tests/v1/kv_offload - - tests/v1/simple_kv_offload - - tests/v1/worker - - tests/v1/streaming_input - - tests/v1/kv_connector/unit - - tests/v1/ec_connector/unit - - tests/v1/metrics - - tests/entrypoints/openai/correctness/test_lmeval.py - - vllm/config/ - - vllm/distributed/ - - vllm/engine/ - - vllm/entrypoints/pooling/ - - vllm/inputs/ - - vllm/lora/ - - vllm/model_executor/ - - vllm/multimodal/ - - vllm/outputs.py - - vllm/platforms/ - - vllm/pooling_params.py - - vllm/profiler/ - - vllm/sampling_params.py - - vllm/tokenizers/ - - vllm/transformers_utils/ - - vllm/utils/ - - vllm/v1/ - optional: true - commands: - # - export HSA_NO_SCRATCH_RECLAIM=1 - - export VLLM_WORKER_MULTIPROC_METHOD=spawn - - pytest -v -s -m 'not cpu_test' v1/core - -- label: ":amd: (MI300) V1 Executor + Worker" - timeout_in_minutes: 60 - mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] - dind: false - agent_pool: mi300_1 - working_dir: /vllm-workspace/tests - source_file_dependencies: - - vllm/ - - tests/v1/core - - tests/v1/executor - - tests/v1/kv_offload - - tests/v1/simple_kv_offload - - tests/v1/worker - - tests/v1/streaming_input - - tests/v1/kv_connector/unit - - tests/v1/ec_connector/unit - - tests/v1/metrics - - tests/entrypoints/openai/correctness/test_lmeval.py - - vllm/config/ - - vllm/distributed/ - - vllm/engine/ - - vllm/entrypoints/pooling/ - - vllm/inputs/ - - vllm/lora/ - - vllm/model_executor/ - - vllm/multimodal/ - - vllm/outputs.py - - vllm/platforms/ - - vllm/pooling_params.py - - vllm/profiler/ - - vllm/sampling_params.py - - vllm/tokenizers/ - - vllm/transformers_utils/ - - vllm/utils/ - - vllm/v1/ - commands: - - export VLLM_WORKER_MULTIPROC_METHOD=spawn - - pytest -v -s v1/executor - - pytest -v -s v1/worker - - pytest -v -s v1/streaming_input - optional: true - -- label: ":amd: (MI300) V1 KV Offload" - timeout_in_minutes: 60 - mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] - dind: false - agent_pool: mi300_1 - working_dir: /vllm-workspace/tests - source_file_dependencies: - - vllm/ - - tests/v1/core - - tests/v1/executor - - tests/v1/kv_offload - - tests/v1/simple_kv_offload - - tests/v1/worker - - tests/v1/streaming_input - - tests/v1/kv_connector/unit - - tests/v1/ec_connector/unit - - tests/v1/metrics - - tests/entrypoints/openai/correctness/test_lmeval.py - - vllm/config/ - - vllm/distributed/ - - vllm/engine/ - - vllm/entrypoints/pooling/ - - vllm/inputs/ - - vllm/lora/ - - vllm/model_executor/ - - vllm/multimodal/ - - vllm/outputs.py - - vllm/platforms/ - - vllm/pooling_params.py - - vllm/profiler/ - - vllm/sampling_params.py - - vllm/tokenizers/ - - vllm/transformers_utils/ - - vllm/utils/ - - vllm/v1/ - commands: - - export VLLM_WORKER_MULTIPROC_METHOD=spawn - - bash /vllm-workspace/.buildkite/scripts/install-kv-offload.sh - - pytest -v -s v1/kv_offload - - pytest -v -s v1/simple_kv_offload - optional: true - -- label: ":amd: (MI300) V1 KV Connectors Shard %N" - timeout_in_minutes: 60 - parallelism: 4 - mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] - dind: false - agent_pool: mi300_1 - working_dir: /vllm-workspace/tests - source_file_dependencies: - - vllm/ - - tests/v1/core - - tests/v1/executor - - tests/v1/kv_offload - - tests/v1/simple_kv_offload - - tests/v1/worker - - tests/v1/streaming_input - - tests/v1/kv_connector/unit - - tests/v1/ec_connector/unit - - tests/v1/metrics - - tests/entrypoints/openai/correctness/test_lmeval.py - - vllm/config/ - - vllm/distributed/ - - vllm/engine/ - - vllm/entrypoints/pooling/ - - vllm/inputs/ - - vllm/lora/ - - vllm/model_executor/ - - vllm/multimodal/ - - vllm/outputs.py - - vllm/platforms/ - - vllm/pooling_params.py - - vllm/profiler/ - - vllm/sampling_params.py - - vllm/tokenizers/ - - vllm/transformers_utils/ - - vllm/utils/ - - vllm/v1/ - commands: - - bash /vllm-workspace/.buildkite/scripts/install-kv-connectors.sh - - export VLLM_WORKER_MULTIPROC_METHOD=spawn - - pytest -v -s -m 'not cpu_test' v1/kv_connector/unit --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB - - pytest -v -s -m 'not cpu_test' v1/ec_connector/unit --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB - optional: true - -- label: ":amd: (MI300) V1 Metrics + LM Eval" - timeout_in_minutes: 65 - mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] - dind: false - agent_pool: mi300_1 - working_dir: /vllm-workspace/tests - source_file_dependencies: - - vllm/ - - tests/v1/core - - tests/v1/executor - - tests/v1/kv_offload - - tests/v1/simple_kv_offload - - tests/v1/worker - - tests/v1/streaming_input - - tests/v1/kv_connector/unit - - tests/v1/ec_connector/unit - - tests/v1/metrics - - tests/entrypoints/openai/correctness/test_lmeval.py - - vllm/config/ - - vllm/distributed/ - - vllm/engine/ - - vllm/entrypoints/pooling/ - - vllm/inputs/ - - vllm/lora/ - - vllm/model_executor/ - - vllm/multimodal/ - - vllm/outputs.py - - vllm/platforms/ - - vllm/pooling_params.py - - vllm/profiler/ - - vllm/sampling_params.py - - vllm/tokenizers/ - - vllm/transformers_utils/ - - vllm/utils/ - - vllm/v1/ - commands: - - export GIT_CONFIG_COUNT=1 - - export GIT_CONFIG_KEY_0=http.version - - export GIT_CONFIG_VALUE_0=HTTP/1.1 - - export GIT_TERMINAL_PROMPT=0 - - export VLLM_WORKER_MULTIPROC_METHOD=spawn - - pytest -v -s -m 'not cpu_test' v1/metrics - - pip install -U git+https://github.com/vllm-project/lm-evaluation-harness.git@streaming-api - - pytest -v -s entrypoints/openai/correctness/test_lmeval.py::test_lm_eval_accuracy_v1_engine - optional: true - - -- label: ":amd: (MI300) V1 Sample" - timeout_in_minutes: 70 - mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] - dind: false - agent_pool: mi300_1 - optional: true - working_dir: "/vllm-workspace/tests" - source_file_dependencies: - - vllm/ - - tests/v1/sample - - tests/v1/logits_processors - - tests/v1/test_oracle.py - - tests/v1/test_request.py - - tests/v1/test_outputs.py - - vllm/config/ - - vllm/distributed/ - - vllm/engine/ - - vllm/inputs/ - - vllm/logger.py - - vllm/model_executor/ - - vllm/platforms/ - - vllm/sampling_params.py - - vllm/transformers_utils/ - - vllm/utils/ - - vllm/v1/ - commands: - - export VLLM_WORKER_MULTIPROC_METHOD=spawn - - pytest -v -s v1/sample - -- label: ":amd: (MI300) V1 Logits + Oracle" - timeout_in_minutes: 70 - mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] - dind: false - agent_pool: mi300_1 - optional: true - working_dir: /vllm-workspace/tests - source_file_dependencies: - - vllm/ - - tests/v1/sample - - tests/v1/logits_processors - - tests/v1/test_oracle.py - - tests/v1/test_request.py - - tests/v1/test_outputs.py - - vllm/config/ - - vllm/distributed/ - - vllm/engine/ - - vllm/inputs/ - - vllm/logger.py - - vllm/model_executor/ - - vllm/platforms/ - - vllm/sampling_params.py - - vllm/transformers_utils/ - - vllm/utils/ - - vllm/v1/ - commands: - - export VLLM_WORKER_MULTIPROC_METHOD=spawn - - pytest -v -s v1/logits_processors - - pytest -v -s v1/test_oracle.py - - pytest -v -s v1/test_request.py - - pytest -v -s v1/test_outputs.py - - - label: ":amd: (MI300) Metrics, Tracing" # TBD timeout_in_minutes: 30 mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] @@ -3342,7 +2667,7 @@ steps: - pytest -v -s distributed/test_utils.py - label: ":amd: (MI300) Hybrid SSM NixlConnector PD accuracy" # TBD - timeout_in_minutes: 60 + timeout_in_minutes: 80 mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] dind: false agent_pool: mi300_4 @@ -3435,8 +2760,43 @@ steps: # # ######################################################################################################################################### +#----------------------------------------------------- mi355 · basic_correctness -----------------------------------------------------# + +- label: ":amd: (MI355 DPX) Basic Correctness" # TBD + timeout_in_minutes: 60 + mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] + dind: false + agent_pool: mi355_dpx + fast_check: true + working_dir: "/vllm-workspace/tests" + source_file_dependencies: + - vllm/ + - tests/basic_correctness/test_basic_correctness + - tests/basic_correctness/test_cpu_offload + - tests/basic_correctness/test_mem.py + optional: true + commands: + - export VLLM_WORKER_MULTIPROC_METHOD=spawn + - pytest -v -s basic_correctness/test_mem.py + - VLLM_TARGET_TEST_SUITE=MI355 pytest -v -s basic_correctness/test_basic_correctness.py + - pytest -v -s basic_correctness/test_cpu_offload.py + #-------------------------------------------------------- mi355 · benchmarks ---------------------------------------------------------# +- label: ":amd: (MI355 DPX) Benchmarks CLI" # TBD + timeout_in_minutes: 40 + mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] + dind: false + agent_pool: mi355_dpx + optional: true + working_dir: "/vllm-workspace/tests" + source_file_dependencies: + - vllm/ + - tests/benchmarks/ + - rust/src/bench/tests/python_serve_flags.txt + commands: + - pytest -v -s benchmarks/ + - label: ":amd: (MI355) Attention Benchmark Smoke" # TBD timeout_in_minutes: 25 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] @@ -3454,11 +2814,11 @@ steps: #---------------------------------------------------------- mi355 · compile ----------------------------------------------------------# -- label: ":amd: (MI355) PyTorch Compilation H100 Cases" +- label: ":amd: (MI355 DPX) PyTorch Compilation H100 Cases" timeout_in_minutes: 45 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] dind: false - agent_pool: mi355_1 + agent_pool: mi355_dpx num_gpus: 1 optional: true working_dir: "/vllm-workspace/tests" @@ -3519,11 +2879,27 @@ steps: #-------------------------------------------------------- mi355 · distributed --------------------------------------------------------# -- label: ":amd: (MI355) Sharded RDT Weight Transfer" +- label: ":amd: (MI355 DPX) EPLB Algorithm" # TBD + timeout_in_minutes: 30 + mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] + dind: false + agent_pool: mi355_dpx + optional: true + working_dir: "/vllm-workspace/tests" + source_file_dependencies: + - vllm/distributed/eplb + - tests/distributed/test_eplb_algo.py + - tests/distributed/test_eplb_utils.py + - vllm/platforms/rocm.py + commands: + - pytest -v -s distributed/test_eplb_algo.py + - pytest -v -s distributed/test_eplb_utils.py + +- label: ":amd: (MI355 DPX) Sharded RDT Weight Transfer" timeout_in_minutes: 45 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] dind: false - agent_pool: mi355_1 + agent_pool: mi355_dpx num_gpus: 1 optional: true working_dir: "/vllm-workspace/tests" @@ -3852,14 +3228,63 @@ steps: DECODER_KV_LAYOUT= bash v1/kv_connector/nixl_integration/run_accuracy_test.sh +#---------------------------------------------------------- mi355 · engine -----------------------------------------------------------# + +- label: ":amd: (MI355 DPX) Engine Core" # TBD + timeout_in_minutes: 40 + mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] + dind: false + agent_pool: mi355_dpx + optional: true + working_dir: "/vllm-workspace/tests" + source_file_dependencies: + - vllm/ + - tests/engine + - tests/test_sequence + - tests/test_config + - tests/test_logger + - tests/test_vllm_port + - tests/jit_monitor/test_hooks.py + - tests/jit_monitor/test_hooks_gpu.py + - vllm/compilation/ + - vllm/config/ + - vllm/engine/ + - vllm/entrypoints/logger.py + - vllm/envs.py + - vllm/logger.py + - vllm/logging_utils/ + - vllm/platforms/ + - vllm/sequence.py + - vllm/triton_utils/ + - vllm/utils/ + commands: + - pytest -v -s engine test_sequence.py test_config.py test_logger.py test_vllm_port.py jit_monitor/test_hooks.py jit_monitor/test_hooks_gpu.py + #-------------------------------------------------------- mi355 · entrypoints --------------------------------------------------------# -- label: ":amd: (MI355) Entrypoints Integration (API Server) %N" +- label: ":amd: (MI355 DPX) Entrypoints Integration (LLM)" # TBD + timeout_in_minutes: 90 + mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] + dind: false + agent_pool: mi355_dpx + optional: true + fast_check: true + working_dir: "/vllm-workspace/tests" + source_file_dependencies: + - vllm/ + - tests/entrypoints/llm + commands: + - export VLLM_WORKER_MULTIPROC_METHOD=spawn + - pytest -v -s entrypoints/llm --ignore=entrypoints/llm/test_generate.py --ignore=entrypoints/llm/test_collective_rpc.py --ignore=entrypoints/llm/offline_mode + - pytest -v -s entrypoints/llm/test_generate.py # it needs a clean process + - pytest -v -s entrypoints/llm/offline_mode # Needs to avoid interference with other tests + +- label: ":amd: (MI355 DPX) Entrypoints Integration (API Server) %N" timeout_in_minutes: 65 parallelism: 4 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] dind: false - agent_pool: mi355_1 + agent_pool: mi355_dpx optional: true fast_check: true working_dir: "/vllm-workspace/tests" @@ -3873,11 +3298,11 @@ steps: - if [ "$$BUILDKITE_PARALLEL_JOB" = "1" ]; then PYTHONPATH=/vllm-workspace pytest -v -s entrypoints/serve/dev/rpc; fi - pytest -v -s entrypoints/scale_out --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB -- label: ":amd: (MI355) Entrypoints Integration (OpenAI API completion)" # TBD +- label: ":amd: (MI355 DPX) Entrypoints Integration (OpenAI API completion)" # TBD timeout_in_minutes: 65 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] dind: false - agent_pool: mi355_1 + agent_pool: mi355_dpx fast_check: true optional: true working_dir: "/vllm-workspace/tests" @@ -3889,11 +3314,11 @@ steps: - pytest -v -s entrypoints/openai/completion --ignore=entrypoints/openai/completion/test_tensorizer_entrypoint.py - pytest -v -s entrypoints/openai --ignore=entrypoints/openai/completion --ignore=entrypoints/openai/chat_completion --ignore=entrypoints/openai/responses --ignore=entrypoints/openai/correctness -- label: ":amd: (MI355) Entrypoints Integration (OpenAI API chat_completion)" # TBD +- label: ":amd: (MI355 DPX) Entrypoints Integration (OpenAI API chat_completion)" # TBD timeout_in_minutes: 70 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] dind: false - agent_pool: mi355_1 + agent_pool: mi355_dpx fast_check: true optional: true working_dir: "/vllm-workspace/tests" @@ -3904,11 +3329,103 @@ steps: - export VLLM_WORKER_MULTIPROC_METHOD=spawn - pytest -v -s entrypoints/openai/chat_completion -- label: ":amd: (MI355) Entrypoints Integration (API Server Generate)" # TBD +- label: ":amd: (MI355 DPX) Entrypoints Integration (API Server Generate)" # TBD timeout_in_minutes: 65 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] dind: false - agent_pool: mi355_1 + agent_pool: mi355_dpx + optional: true + fast_check: true + working_dir: "/vllm-workspace/tests" + source_file_dependencies: + - vllm/ + - tests/tool_use + - tests/entrypoints/tool_parsers + - tests/entrypoints/anthropic + - tests/entrypoints/cohere + - tests/entrypoints/generate + commands: + - pytest -v -s tool_use + - pytest -v -s entrypoints/tool_parsers + - pytest -v -s entrypoints/generate + - pytest -v -s entrypoints/anthropic + - pytest -v -s entrypoints/cohere + +- label: ":amd: (MI355 DPX) OpenAI API Correctness" # TBD + timeout_in_minutes: 30 + mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] + dind: false + agent_pool: mi355_dpx + optional: true + working_dir: "/vllm-workspace/tests" + source_file_dependencies: + - csrc/ + - vllm/entrypoints/openai/ + - vllm/model_executor/layers/ + - vllm/v1/attention/backends/ + - vllm/v1/attention/selector.py + - vllm/_aiter_ops.py + - vllm/platforms/rocm.py + - vllm/model_executor/model_loader/ + commands: + - bash ../tools/install_torchcodec_rocm.sh || exit 1 + - pytest -s entrypoints/openai/correctness/ + +- label: ":amd: (MI355 DPX) Entrypoints Integration (API Server) %N (MI355 suite)" + timeout_in_minutes: 65 + parallelism: 4 + mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] + dind: false + agent_pool: mi355_dpx + optional: true + fast_check: true + working_dir: "/vllm-workspace/tests" + source_file_dependencies: + - vllm/ + - tests/entrypoints/serve + - tests/entrypoints/scale_out + commands: + - export VLLM_WORKER_MULTIPROC_METHOD=spawn + - pytest -v -s entrypoints/serve --ignore=entrypoints/serve/dev/rpc --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB + - if [ "$$BUILDKITE_PARALLEL_JOB" = "1" ]; then PYTHONPATH=/vllm-workspace pytest -v -s entrypoints/serve/dev/rpc; fi + - pytest -v -s entrypoints/scale_out --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB + +- label: ":amd: (MI355 DPX) Entrypoints Integration (OpenAI API completion) (MI355 suite)" # TBD + timeout_in_minutes: 65 + mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] + dind: false + agent_pool: mi355_dpx + fast_check: true + optional: true + working_dir: "/vllm-workspace/tests" + source_file_dependencies: + - vllm/ + - tests/entrypoints/openai + commands: + - export VLLM_WORKER_MULTIPROC_METHOD=spawn + - pytest -v -s entrypoints/openai/completion --ignore=entrypoints/openai/completion/test_tensorizer_entrypoint.py + - pytest -v -s entrypoints/openai --ignore=entrypoints/openai/completion --ignore=entrypoints/openai/chat_completion --ignore=entrypoints/openai/responses --ignore=entrypoints/openai/correctness + +- label: ":amd: (MI355 DPX) Entrypoints Integration (OpenAI API chat_completion) (MI355 suite)" # TBD + timeout_in_minutes: 70 + mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] + dind: false + agent_pool: mi355_dpx + fast_check: true + optional: true + working_dir: "/vllm-workspace/tests" + source_file_dependencies: + - vllm/ + - tests/entrypoints/openai + commands: + - export VLLM_WORKER_MULTIPROC_METHOD=spawn + - pytest -v -s entrypoints/openai/chat_completion + +- label: ":amd: (MI355 DPX) Entrypoints Integration (API Server Generate) (MI355 suite)" # TBD + timeout_in_minutes: 65 + mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] + dind: false + agent_pool: mi355_dpx fast_check: true optional: true working_dir: "/vllm-workspace/tests" @@ -3926,11 +3443,11 @@ steps: - pytest -v -s entrypoints/anthropic - pytest -v -s entrypoints/cohere -- label: ":amd: (MI355) Entrypoints Integration (Speech to Text)" # TBD +- label: ":amd: (MI355 DPX) Entrypoints Integration (Speech to Text)" # TBD timeout_in_minutes: 60 - mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi355] + mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] dind: false - agent_pool: mi355_1 + agent_pool: mi355_dpx fast_check: true working_dir: "/vllm-workspace/tests" source_file_dependencies: @@ -3941,11 +3458,11 @@ steps: - export VLLM_WORKER_MULTIPROC_METHOD=spawn - pytest -v -s entrypoints/speech_to_text -- label: ":amd: (MI355) Entrypoints Integration (Multimodal)" +- label: ":amd: (MI355 DPX) Entrypoints Integration (Multimodal)" timeout_in_minutes: 55 - mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi355] + mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] dind: false - agent_pool: mi355_1 + agent_pool: mi355_dpx fast_check: true working_dir: "/vllm-workspace/tests" source_file_dependencies: @@ -3956,11 +3473,11 @@ steps: - export VLLM_WORKER_MULTIPROC_METHOD=spawn - pytest -v -s entrypoints/multimodal -- label: ":amd: (MI355) Entrypoints Integration (Pooling) Shard %N" # TBD +- label: ":amd: (MI355 DPX) Entrypoints Integration (Pooling) Shard %N" # TBD timeout_in_minutes: 65 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] dind: false - agent_pool: mi355_1 + agent_pool: mi355_dpx fast_check: true parallelism: 4 working_dir: "/vllm-workspace/tests" @@ -3974,6 +3491,22 @@ steps: #----------------------------------------------------------- mi355 · evals -----------------------------------------------------------# +- label: ":amd: (MI355 DPX) Multimodal Accuracy Eval (Small Models)" # TBD + timeout_in_minutes: 35 + mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] + dind: false + agent_pool: mi355_dpx + optional: true + working_dir: "/vllm-workspace/.buildkite/lm-eval-harness" + source_file_dependencies: + - vllm/multimodal/ + - vllm/inputs/ + - vllm/v1/core/ + - vllm/platforms/rocm.py + - vllm/model_executor/model_loader/ + commands: + - pytest -s -v test_lm_eval_correctness.py --config-list-file=configs/models-mm-small.txt --tp-size=1 + - label: ":amd: (MI355) GPQA Eval (GPT-OSS)" # TBD timeout_in_minutes: 40 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] @@ -3997,11 +3530,11 @@ steps: - uv pip install --system 'gpt-oss[eval]==0.0.5' - pytest -s -v evals/gpt_oss/test_gpqa_correctness.py --config-list-file=configs/models-gfx950.txt -- label: ":amd: (MI355) LM Eval Watermarking" +- label: ":amd: (MI355 DPX) LM Eval Watermarking" timeout_in_minutes: 45 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] dind: false - agent_pool: mi355_1 + agent_pool: mi355_dpx num_gpus: 1 optional: true working_dir: "/vllm-workspace/tests" @@ -4298,6 +3831,41 @@ steps: #--------------------------------------------------------- mi355 · examples ----------------------------------------------------------# +- label: ":amd: (MI355 DPX) Examples" # TBD + timeout_in_minutes: 75 + mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] + dind: false + agent_pool: mi355_dpx + optional: true + working_dir: "/vllm-workspace/examples" + source_file_dependencies: + - vllm/entrypoints + - vllm/multimodal + - examples/ + - vllm/platforms/rocm.py + commands: + # Basic + # Multi-modal models + # Pooling models + # Features demo + - pip install --no-deps tensorizer + - python3 basic/offline_inference/chat.py + - python3 basic/offline_inference/generate.py --model facebook/opt-125m + - python3 basic/offline_inference/generate.py --model meta-llama/Llama-2-13b-chat-hf --cpu-offload-gb 10 + - python3 basic/offline_inference/classify.py + - python3 basic/offline_inference/embed.py + - python3 basic/offline_inference/score.py + - python3 generate/multimodal/audio_language_offline.py --seed 0 + - python3 generate/multimodal/vision_language_offline.py --seed 0 + - python3 generate/multimodal/vision_language_multi_image_offline.py --seed 0 + - python3 generate/multimodal/encoder_decoder_multimodal_offline.py --model-type whisper --seed 0 + - python3 pooling/embed/vision_embedding_offline.py --seed 0 + - python3 features/automatic_prefix_caching/prefix_caching_offline.py + - python3 deployment/llm_engine_example.py + - python3 features/tensorize_vllm_model.py --model facebook/opt-125m serialize --serialized-directory /tmp/ --suffix v1 && python3 features/tensorize_vllm_model.py --model facebook/opt-125m deserialize --path-to-tensors /tmp/vllm/facebook/opt-125m/v1/model.tensors + - python3 features/speculative_decoding/spec_decode_offline.py --test --method eagle --num_spec_tokens 3 --dataset-name hf --dataset-path philschmid/mt-bench --num-prompts 80 --temp 0 --top-p 1.0 --top-k -1 --tp 1 --enable-chunked-prefill --max-model-len 2048 + - python3 features/speculative_decoding/spec_decode_offline.py --test --method eagle3 --num_spec_tokens 3 --dataset-name hf --dataset-path philschmid/mt-bench --num-prompts 80 --temp 0 --top-p 1.0 --top-k -1 --tp 1 --enable-chunked-prefill --max-model-len 1536 + - label: ":amd: (MI355) Examples" # TBD timeout_in_minutes: 75 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] @@ -4335,11 +3903,11 @@ steps: #---------------------------------------------------------- mi355 · kernels ----------------------------------------------------------# -- label: ":amd: (MI355) Attention DiffKV Kernels" +- label: ":amd: (MI355 DPX) Attention DiffKV Kernels" timeout_in_minutes: 35 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] dind: false - agent_pool: mi355_1 + agent_pool: mi355_dpx num_gpus: 1 optional: true working_dir: "/vllm-workspace/tests" @@ -4352,29 +3920,6 @@ steps: commands: - pytest -v -s kernels/attention/test_triton_unified_attention_diffkv.py -- label: ":amd: (MI355) Core Operation Kernels Shard %N" # TBD - timeout_in_minutes: 40 - mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] - dind: false - agent_pool: mi355_1 - parallelism: 3 - working_dir: "/vllm-workspace/tests" - source_file_dependencies: - - csrc/ - - tests/kernels/core - - tests/kernels/test_top_k_per_row.py - - tests/kernels/test_concat_mla_q.py - - tests/kernels/test_rocm_fp32_router_gemm.py - - vllm/model_executor/layers/fused_moe/router/gate_linear.py - - vllm/model_executor/layers/fused_moe/router/rocm_fp32_router_gemm.py - - vllm/model_executor/layers/rotary_embedding/ - - vllm/_aiter_ops.py - - vllm/platforms/rocm.py - - tests/kernels/test_fused_qk_norm_rope_gate.py - optional: true - commands: - - pytest -v -s kernels/core --ignore=kernels/core/test_minimax_reduce_rms.py kernels/test_fused_qk_norm_rope_gate.py kernels/test_concat_mla_q.py kernels/test_top_k_per_row.py kernels/test_rocm_fp32_router_gemm.py --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT - - label: ":amd: (MI355) MiniMax Reduce RMS Kernels" # TBD timeout_in_minutes: 45 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] @@ -4399,11 +3944,11 @@ steps: commands: - pytest -v -s kernels/core/test_minimax_reduce_rms.py -- label: ":amd: (MI355) Kernels" # TBD +- label: ":amd: (MI355 DPX) Kernels" # TBD timeout_in_minutes: 25 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] dind: false - agent_pool: mi355_1 + agent_pool: mi355_dpx working_dir: "/vllm-workspace/" source_file_dependencies: - csrc/quantization/fp4/ @@ -4427,11 +3972,11 @@ steps: - python3 examples/basic/offline_inference/chat.py --attention-backend TRITON_ATTN - pytest -v -s tests/kernels/attention/test_attention_selector.py -- label: ":amd: (MI355) MLA Kernels" +- label: ":amd: (MI355 DPX) MLA Kernels" timeout_in_minutes: 40 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] dind: false - agent_pool: mi355_1 + agent_pool: mi355_dpx num_gpus: 1 optional: true working_dir: "/vllm-workspace/" @@ -4451,11 +3996,11 @@ steps: - pytest -v -s tests/kernels/attention/test_rocm_aiter_mla_fp8_support.py - pytest -v -s tests/kernels/attention/test_rocm_aiter_mla_op_registration.py -- label: ":amd: (MI355) DeepSeek V4 Fused Kernels" +- label: ":amd: (MI355 DPX) DeepSeek V4 Fused Kernels" timeout_in_minutes: 60 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] dind: false - agent_pool: mi355_1 + agent_pool: mi355_dpx num_gpus: 1 optional: true working_dir: "/vllm-workspace/tests" @@ -4467,11 +4012,11 @@ steps: commands: - pytest -v -s kernels/test_fused_deepseek_v4_qnorm_rope_kv_insert.py -- label: ":amd: (MI355) Attention Kernels Shard %N" # TBD +- label: ":amd: (MI355 DPX) Attention Kernels Shard %N" # TBD timeout_in_minutes: 90 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] dind: false - agent_pool: mi355_1 + agent_pool: mi355_dpx parallelism: 2 working_dir: "/vllm-workspace/tests" source_file_dependencies: @@ -4487,11 +4032,11 @@ steps: commands: - pytest -v -s kernels/attention --ignore=kernels/attention/test_triton_unified_attention_diffkv.py --ignore=kernels/attention/test_rocm_aiter_mla_decode.py --ignore=kernels/attention/test_rocm_aiter_mla_decode_metadata.py --ignore=kernels/attention/test_rocm_aiter_mla_fp8_support.py --ignore=kernels/attention/test_rocm_aiter_mla_op_registration.py --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT -- label: ":amd: (MI355) MoE Kernels Shard %N" # TBD +- label: ":amd: (MI355 DPX) MoE Kernels Shard %N (MI355 suite)" # TBD timeout_in_minutes: 55 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] dind: false - agent_pool: mi355_1 + agent_pool: mi355_dpx parallelism: 5 working_dir: "/vllm-workspace/tests" source_file_dependencies: @@ -4631,11 +4176,11 @@ steps: - amd-smi - pytest -v -s kernels/quantization/test_nvfp4_emulation.py -k test_nvfp4_dense_emulation --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT -- label: ":amd: (MI355) FP8 MoE Kernels" # TBD +- label: ":amd: (MI355 DPX) FP8 MoE Kernels" # TBD timeout_in_minutes: 40 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] dind: false - agent_pool: mi355_1 + agent_pool: mi355_dpx working_dir: "/vllm-workspace/tests" source_file_dependencies: - csrc/moe/ @@ -4678,13 +4223,50 @@ steps: commands: - pytest -v -s kernels/moe/test_deepep_moe.py +#----------------------------------------------------------- mi355 · lora ------------------------------------------------------------# + +- label: ":amd: (MI355 DPX) LoRA Shard %N" # TBD + timeout_in_minutes: 85 + mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] + dind: false + agent_pool: mi355_dpx + parallelism: 4 + optional: true + working_dir: "/vllm-workspace/tests" + source_file_dependencies: + - vllm/lora + - tests/lora + - vllm/platforms/rocm.py + commands: + - pytest -v -s lora --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --ignore=lora/test_chatglm3_tp.py --ignore=lora/test_llama_tp.py --ignore=lora/test_qwen3_with_multi_loras.py --ignore=lora/test_olmoe_tp.py --ignore=lora/test_deepseekv2_tp.py --ignore=lora/test_gptoss_tp.py --ignore=lora/test_qwen3moe_tp.py --ignore=lora/test_qwen35_densemodel_lora.py + #------------------------------------------------------ mi355 · models / basic -------------------------------------------------------# -- label: ":amd: (MI355) GLM5Next" +- label: ":amd: (MI355 DPX) Basic Models (Other)" # TBD + timeout_in_minutes: 65 + mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] + dind: false + agent_pool: mi355_dpx + optional: true + working_dir: "/vllm-workspace/tests" + source_file_dependencies: + - vllm/ + - tests/models/test_terratorch.py + - tests/models/transformers/test_backend.py + - tests/models/test_registry.py + - tests/models/test_hyv4_rocm.py + - tests/models/test_vision.py + - tests/models/test_deepseek_v4_vl_rocm.py + commands: + - pytest -v -s models/test_terratorch.py models/transformers/test_backend.py models/test_registry.py models/test_deepseek_v4_vl_rocm.py + - VLLM_ROCM_USE_AITER=1 pytest -v -s models/test_hyv4_rocm.py -m 'not distributed' + - pytest -v -s models/test_vision.py::test_simple_mrope_vision_model_spatial_merge + +- label: ":amd: (MI355 DPX) GLM5Next" timeout_in_minutes: 35 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] dind: false - agent_pool: mi355_1 + agent_pool: mi355_dpx num_gpus: 1 optional: true working_dir: "/vllm-workspace/tests" @@ -4695,11 +4277,11 @@ steps: commands: - pytest -v -s models/glm5next -- label: ":amd: (MI355) Basic Models (Extra Initialization) Shard %N" # TBD +- label: ":amd: (MI355 DPX) Basic Models (Extra Initialization) Shard %N" # TBD timeout_in_minutes: 60 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] dind: false - agent_pool: mi355_1 + agent_pool: mi355_dpx parallelism: 6 working_dir: "/vllm-workspace/tests" source_file_dependencies: @@ -4715,11 +4297,48 @@ steps: #----------------------------------------------------- mi355 · models / language -----------------------------------------------------# -- label: ":amd: (MI355) Language Models (Hybrid) Shard %N" # TBD +- label: ":amd: (MI355 DPX) Language Models (Standard)" # TBD + timeout_in_minutes: 60 + mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] + dind: false + agent_pool: mi355_dpx + optional: true + working_dir: "/vllm-workspace/tests" + source_file_dependencies: + - vllm/ + - tests/models/language + commands: + - pip freeze | grep -E 'torch' + - pytest -v -s models/language -m 'core_model and (not slow_test)' + +- label: ":amd: (MI355 DPX) Language Models (Extra Standard) Shard %N" # TBD + timeout_in_minutes: 40 + mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] + dind: false + agent_pool: mi355_dpx + optional: true + parallelism: 2 + working_dir: "/vllm-workspace/tests" + source_file_dependencies: + - vllm/model_executor/models/ + - vllm/model_executor/model_loader/ + - vllm/model_executor/layers/ + - vllm/v1/attention/backends/ + - vllm/v1/attention/selector.py + - tests/models/language/pooling/test_embedding.py + - tests/models/language/generation/test_common.py + - tests/models/language/pooling/test_classification.py + - vllm/_aiter_ops.py + - vllm/platforms/rocm.py + commands: + - pip freeze | grep -E 'torch' + - pytest -v -s models/language -m 'core_model and slow_test' --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB + +- label: ":amd: (MI355 DPX) Language Models (Hybrid) Shard %N" # TBD timeout_in_minutes: 65 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] dind: false - agent_pool: mi355_1 + agent_pool: mi355_dpx parallelism: 2 optional: true working_dir: "/vllm-workspace/tests" @@ -4734,11 +4353,11 @@ steps: - CAUSAL_CONV1D_FORCE_BUILD=TRUE uv pip install --system --no-build-isolation 'git+https://github.com/Dao-AILab/causal-conv1d@v1.6.0' - pytest -v -s models/language/generation -m hybrid_model -k 'not granite-4.0-tiny-preview' --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB -- label: ":amd: (MI355) Granite Language Model Compatibility" +- label: ":amd: (MI355 DPX) Granite Language Model Compatibility" timeout_in_minutes: 80 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] dind: false - agent_pool: mi355_1 + agent_pool: mi355_dpx num_gpus: 1 optional: true working_dir: "/vllm-workspace/tests" @@ -4754,11 +4373,11 @@ steps: - CAUSAL_CONV1D_FORCE_BUILD=TRUE uv pip install --system --no-build-isolation 'git+https://github.com/Dao-AILab/causal-conv1d@v1.6.0' - pytest -v -s models/language/generation -m hybrid_model -k 'granite-4.0-tiny-preview' -- label: ":amd: (MI355) Language Models (Extended Generation)" # TBD +- label: ":amd: (MI355 DPX) Language Models (Extended Generation)" # TBD timeout_in_minutes: 95 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] dind: false - agent_pool: mi355_1 + agent_pool: mi355_dpx working_dir: "/vllm-workspace/tests" source_file_dependencies: - vllm/ @@ -4769,12 +4388,12 @@ steps: - CAUSAL_CONV1D_FORCE_BUILD=TRUE uv pip install --system --no-build-isolation 'git+https://github.com/Dao-AILab/causal-conv1d@v1.6.0' - pytest -v -s models/language/generation -m '(not core_model) and (not hybrid_model)' -- label: ":amd: (MI355) Language Models (Extended Pooling) Shard %N" +- label: ":amd: (MI355 DPX) Language Models (Extended Pooling) Shard %N" timeout_in_minutes: 95 parallelism: 4 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] dind: false - agent_pool: mi355_1 + agent_pool: mi355_dpx optional: true working_dir: "/vllm-workspace/tests" source_file_dependencies: @@ -4783,11 +4402,11 @@ steps: commands: - pytest -v -s models/language/pooling -m 'not core_model' --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB -- label: ":amd: (MI355) Language Models (PPL)" # TBD +- label: ":amd: (MI355 DPX) Language Models (PPL)" # TBD timeout_in_minutes: 65 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] dind: false - agent_pool: mi355_1 + agent_pool: mi355_dpx optional: true working_dir: "/vllm-workspace/tests" source_file_dependencies: @@ -4814,11 +4433,11 @@ steps: commands: - pytest -v -s models/language/generation_ppl_test -- label: ":amd: (MI355) Language Models (Standard)" # TBD +- label: ":amd: (MI355 DPX) Language Models (Standard) (MI355 suite)" # TBD timeout_in_minutes: 60 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] dind: false - agent_pool: mi355_1 + agent_pool: mi355_dpx working_dir: "/vllm-workspace/tests" source_file_dependencies: - vllm/ @@ -4830,11 +4449,40 @@ steps: #---------------------------------------------------- mi355 · models / multimodal ----------------------------------------------------# -- label: ":amd: (MI355) Multimodal Models (Extended Generation 1)" # TBD +- label: ":amd: (MI355 DPX) Multimodal Models (Standard) 1: qwen2" # TBD + timeout_in_minutes: 65 + mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] + dind: false + agent_pool: mi355_dpx + optional: true + working_dir: "/vllm-workspace/tests" + source_file_dependencies: + - vllm/ + - tests/models/multimodal + commands: + - pytest -v -s models/multimodal/generation/test_common.py -m core_model -k "qwen2" + - pytest -v -s models/multimodal/generation/test_ultravox.py -m core_model + +- label: ":amd: (MI355 DPX) Multimodal Models (Standard) 2: qwen3 + gemma" # TBD + timeout_in_minutes: 55 + mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] + dind: false + agent_pool: mi355_dpx + optional: true + working_dir: "/vllm-workspace/tests" + source_file_dependencies: + - vllm/ + - tests/models/multimodal + commands: + - pytest -v -s models/multimodal/generation/test_common.py -m core_model -k "qwen3 or gemma" + - pytest -v -s models/multimodal/generation/test_mm_prefix_lm.py -m core_model + - pytest -v -s models/multimodal/generation/test_qwen2_5_vl.py -m core_model + +- label: ":amd: (MI355 DPX) Multimodal Models (Extended Generation 1)" # TBD timeout_in_minutes: 90 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] dind: false - agent_pool: mi355_1 + agent_pool: mi355_dpx optional: true working_dir: "/vllm-workspace/tests" source_file_dependencies: @@ -4845,11 +4493,11 @@ steps: - pytest -v -s models/multimodal/generation -m 'not core_model' --ignore models/multimodal/generation/test_common.py - pytest -v -s models/multimodal/test_mapping.py -- label: ":amd: (MI355) Multimodal Models (Extended Generation 3)" # TBD +- label: ":amd: (MI355 DPX) Multimodal Models (Extended Generation 3)" # TBD timeout_in_minutes: 90 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] dind: false - agent_pool: mi355_1 + agent_pool: mi355_dpx optional: true working_dir: "/vllm-workspace/tests" source_file_dependencies: @@ -4858,11 +4506,11 @@ steps: commands: - pytest -v -s models/multimodal/generation/test_common.py -m 'split(group=1) and not core_model' -- label: ":amd: (MI355) Multimodal Models (Extended Pooling)" # TBD +- label: ":amd: (MI355 DPX) Multimodal Models (Extended Pooling)" # TBD timeout_in_minutes: 75 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] dind: false - agent_pool: mi355_1 + agent_pool: mi355_dpx optional: true working_dir: "/vllm-workspace/tests" source_file_dependencies: @@ -4871,11 +4519,11 @@ steps: commands: - pytest -v -s models/multimodal/pooling -m 'not core_model' -- label: ":amd: (MI355) Multimodal Models (Standard) 1: qwen2" # TBD +- label: ":amd: (MI355 DPX) Multimodal Models (Standard) 1: qwen2 (MI355 suite)" # TBD timeout_in_minutes: 65 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] dind: false - agent_pool: mi355_1 + agent_pool: mi355_dpx optional: true working_dir: "/vllm-workspace/tests" source_file_dependencies: @@ -4885,11 +4533,11 @@ steps: - pytest -v -s models/multimodal/generation/test_common.py -m core_model -k "qwen2" - pytest -v -s models/multimodal/generation/test_ultravox.py -m core_model -- label: ":amd: (MI355) Multimodal Models (Standard) 4: other + whisper" # TBD +- label: ":amd: (MI355 DPX) Multimodal Models (Standard) 4: other + whisper" # TBD timeout_in_minutes: 70 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] dind: false - agent_pool: mi355_1 + agent_pool: mi355_dpx optional: true working_dir: "/vllm-workspace/tests" source_file_dependencies: @@ -4903,11 +4551,11 @@ steps: #----------------------------------------------------- mi355 · models / quantized -----------------------------------------------------# -- label: ":amd: (MI355) Quantized Models" # TBD +- label: ":amd: (MI355 DPX) Quantized Models" # TBD timeout_in_minutes: 80 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] dind: false - agent_pool: mi355_1 + agent_pool: mi355_dpx working_dir: "/vllm-workspace/tests" source_file_dependencies: - vllm/model_executor/layers/quantization @@ -4975,11 +4623,11 @@ steps: #--------------------------------------------------------- mi355 · samplers ----------------------------------------------------------# -- label: ":amd: (MI355) Samplers Multimodal Beam Search" +- label: ":amd: (MI355 DPX) Samplers Multimodal Beam Search" timeout_in_minutes: 45 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] dind: false - agent_pool: mi355_1 + agent_pool: mi355_dpx num_gpus: 1 optional: true working_dir: "/vllm-workspace/tests" @@ -4997,11 +4645,363 @@ steps: #------------------------------------------------------------ mi355 · v1 -------------------------------------------------------------# -- label: ":amd: (MI355) E2E Core Large Memory" +- label: ":amd: (MI355 DPX) Spec Decode Draft Model" # TBD + timeout_in_minutes: 60 + mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] + dind: false + agent_pool: mi355_dpx + optional: true + working_dir: "/vllm-workspace/tests" + source_file_dependencies: + - vllm/v1/spec_decode/ + - vllm/v1/worker/gpu/spec_decode/ + - vllm/model_executor/model_loader/ + - vllm/v1/sample/ + - vllm/model_executor/layers/ + - tests/v1/e2e/spec_decode/ + - vllm/platforms/rocm.py + commands: + - pytest -v -s v1/e2e/spec_decode/draft_model/ + +- label: ":amd: (MI355 DPX) Spec Decode Eagle 1: DeepSeek + Qwen" + timeout_in_minutes: 60 + mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] + dind: false + agent_pool: mi355_dpx + optional: true + working_dir: "/vllm-workspace/tests" + source_file_dependencies: + - vllm/v1/spec_decode/ + - vllm/v1/worker/gpu/spec_decode/ + - vllm/model_executor/model_loader/ + - vllm/v1/sample/ + - vllm/model_executor/layers/ + - tests/v1/e2e/spec_decode/ + - vllm/platforms/rocm.py + commands: + - pytest -v -s v1/e2e/spec_decode/eagle/ -k "deepseek_eagle or qwen3_eagle3" + +- label: ":amd: (MI355 DPX) Spec Decode Eagle 2: Llama 3 + Qwen VL + Other" + timeout_in_minutes: 60 + mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] + dind: false + agent_pool: mi355_dpx + optional: true + working_dir: /vllm-workspace/tests + source_file_dependencies: + - vllm/v1/spec_decode/ + - vllm/v1/worker/gpu/spec_decode/ + - vllm/model_executor/model_loader/ + - vllm/v1/sample/ + - vllm/model_executor/layers/ + - tests/v1/e2e/spec_decode/ + - vllm/platforms/rocm.py + commands: + - pytest -v -s v1/e2e/spec_decode/eagle/ -k "not deepseek_eagle and not qwen3_eagle3" + + +- label: ":amd: (MI355 DPX) Spec Decode N-Gram + Suffix" # TBD + timeout_in_minutes: 35 + mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] + dind: false + agent_pool: mi355_dpx + optional: true + working_dir: "/vllm-workspace/tests" + source_file_dependencies: + - vllm/v1/spec_decode/ + - vllm/v1/worker/gpu/spec_decode/ + - vllm/model_executor/model_loader/ + - vllm/v1/sample/ + - vllm/model_executor/layers/ + - tests/v1/e2e/spec_decode/ + - tests/spec_decode/ + - vllm/platforms/rocm.py + commands: + - pytest -v -s v1/e2e/spec_decode/ngram_suffix/ + - python3 spec_decode/test_custom_proposer.py + +- label: ":amd: (MI355 DPX) V1 Core" + timeout_in_minutes: 60 + mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] + dind: false + agent_pool: mi355_dpx + working_dir: "/vllm-workspace/tests" + source_file_dependencies: + - vllm/ + - tests/v1/core + - tests/v1/executor + - tests/v1/kv_offload + - tests/v1/simple_kv_offload + - tests/v1/worker + - tests/v1/streaming_input + - tests/v1/kv_connector/unit + - tests/v1/ec_connector/unit + - tests/v1/metrics + - tests/entrypoints/openai/correctness/test_lmeval.py + - vllm/config/ + - vllm/distributed/ + - vllm/engine/ + - vllm/entrypoints/pooling/ + - vllm/inputs/ + - vllm/lora/ + - vllm/model_executor/ + - vllm/multimodal/ + - vllm/outputs.py + - vllm/platforms/ + - vllm/pooling_params.py + - vllm/profiler/ + - vllm/sampling_params.py + - vllm/tokenizers/ + - vllm/transformers_utils/ + - vllm/utils/ + - vllm/v1/ + optional: true + commands: + # - export HSA_NO_SCRATCH_RECLAIM=1 + - export VLLM_WORKER_MULTIPROC_METHOD=spawn + - pytest -v -s -m 'not cpu_test' v1/core + +- label: ":amd: (MI355 DPX) V1 Executor + Worker" + timeout_in_minutes: 60 + mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] + dind: false + agent_pool: mi355_dpx + working_dir: /vllm-workspace/tests + source_file_dependencies: + - vllm/ + - tests/v1/core + - tests/v1/executor + - tests/v1/kv_offload + - tests/v1/simple_kv_offload + - tests/v1/worker + - tests/v1/streaming_input + - tests/v1/kv_connector/unit + - tests/v1/ec_connector/unit + - tests/v1/metrics + - tests/entrypoints/openai/correctness/test_lmeval.py + - vllm/config/ + - vllm/distributed/ + - vllm/engine/ + - vllm/entrypoints/pooling/ + - vllm/inputs/ + - vllm/lora/ + - vllm/model_executor/ + - vllm/multimodal/ + - vllm/outputs.py + - vllm/platforms/ + - vllm/pooling_params.py + - vllm/profiler/ + - vllm/sampling_params.py + - vllm/tokenizers/ + - vllm/transformers_utils/ + - vllm/utils/ + - vllm/v1/ + commands: + - export VLLM_WORKER_MULTIPROC_METHOD=spawn + - pytest -v -s v1/executor + - pytest -v -s v1/worker + - pytest -v -s v1/streaming_input + optional: true + +- label: ":amd: (MI355 DPX) V1 KV Offload" + timeout_in_minutes: 60 + mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] + dind: false + agent_pool: mi355_dpx + working_dir: /vllm-workspace/tests + source_file_dependencies: + - vllm/ + - tests/v1/core + - tests/v1/executor + - tests/v1/kv_offload + - tests/v1/simple_kv_offload + - tests/v1/worker + - tests/v1/streaming_input + - tests/v1/kv_connector/unit + - tests/v1/ec_connector/unit + - tests/v1/metrics + - tests/entrypoints/openai/correctness/test_lmeval.py + - vllm/config/ + - vllm/distributed/ + - vllm/engine/ + - vllm/entrypoints/pooling/ + - vllm/inputs/ + - vllm/lora/ + - vllm/model_executor/ + - vllm/multimodal/ + - vllm/outputs.py + - vllm/platforms/ + - vllm/pooling_params.py + - vllm/profiler/ + - vllm/sampling_params.py + - vllm/tokenizers/ + - vllm/transformers_utils/ + - vllm/utils/ + - vllm/v1/ + commands: + - export VLLM_WORKER_MULTIPROC_METHOD=spawn + - bash /vllm-workspace/.buildkite/scripts/install-kv-offload.sh + - pytest -v -s v1/kv_offload + - pytest -v -s v1/simple_kv_offload + optional: true + +- label: ":amd: (MI355 DPX) V1 KV Connectors Shard %N" + timeout_in_minutes: 60 + parallelism: 4 + mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] + dind: false + agent_pool: mi355_dpx + working_dir: /vllm-workspace/tests + source_file_dependencies: + - vllm/ + - tests/v1/core + - tests/v1/executor + - tests/v1/kv_offload + - tests/v1/simple_kv_offload + - tests/v1/worker + - tests/v1/streaming_input + - tests/v1/kv_connector/unit + - tests/v1/ec_connector/unit + - tests/v1/metrics + - tests/entrypoints/openai/correctness/test_lmeval.py + - vllm/config/ + - vllm/distributed/ + - vllm/engine/ + - vllm/entrypoints/pooling/ + - vllm/inputs/ + - vllm/lora/ + - vllm/model_executor/ + - vllm/multimodal/ + - vllm/outputs.py + - vllm/platforms/ + - vllm/pooling_params.py + - vllm/profiler/ + - vllm/sampling_params.py + - vllm/tokenizers/ + - vllm/transformers_utils/ + - vllm/utils/ + - vllm/v1/ + commands: + - bash /vllm-workspace/.buildkite/scripts/install-kv-connectors.sh + - export VLLM_WORKER_MULTIPROC_METHOD=spawn + - pytest -v -s -m 'not cpu_test' v1/kv_connector/unit --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB + - pytest -v -s -m 'not cpu_test' v1/ec_connector/unit --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB + optional: true + +- label: ":amd: (MI355 DPX) V1 Metrics + LM Eval" timeout_in_minutes: 65 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] dind: false - agent_pool: mi355_1 + agent_pool: mi355_dpx + working_dir: /vllm-workspace/tests + source_file_dependencies: + - vllm/ + - tests/v1/core + - tests/v1/executor + - tests/v1/kv_offload + - tests/v1/simple_kv_offload + - tests/v1/worker + - tests/v1/streaming_input + - tests/v1/kv_connector/unit + - tests/v1/ec_connector/unit + - tests/v1/metrics + - tests/entrypoints/openai/correctness/test_lmeval.py + - vllm/config/ + - vllm/distributed/ + - vllm/engine/ + - vllm/entrypoints/pooling/ + - vllm/inputs/ + - vllm/lora/ + - vllm/model_executor/ + - vllm/multimodal/ + - vllm/outputs.py + - vllm/platforms/ + - vllm/pooling_params.py + - vllm/profiler/ + - vllm/sampling_params.py + - vllm/tokenizers/ + - vllm/transformers_utils/ + - vllm/utils/ + - vllm/v1/ + commands: + - export GIT_CONFIG_COUNT=1 + - export GIT_CONFIG_KEY_0=http.version + - export GIT_CONFIG_VALUE_0=HTTP/1.1 + - export GIT_TERMINAL_PROMPT=0 + - export VLLM_WORKER_MULTIPROC_METHOD=spawn + - pytest -v -s -m 'not cpu_test' v1/metrics + - pip install -U git+https://github.com/vllm-project/lm-evaluation-harness.git@streaming-api + - pytest -v -s entrypoints/openai/correctness/test_lmeval.py::test_lm_eval_accuracy_v1_engine + optional: true + + +- label: ":amd: (MI355 DPX) V1 Sample" + timeout_in_minutes: 70 + mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] + dind: false + agent_pool: mi355_dpx + optional: true + working_dir: "/vllm-workspace/tests" + source_file_dependencies: + - vllm/ + - tests/v1/sample + - tests/v1/logits_processors + - tests/v1/test_oracle.py + - tests/v1/test_request.py + - tests/v1/test_outputs.py + - vllm/config/ + - vllm/distributed/ + - vllm/engine/ + - vllm/inputs/ + - vllm/logger.py + - vllm/model_executor/ + - vllm/platforms/ + - vllm/sampling_params.py + - vllm/transformers_utils/ + - vllm/utils/ + - vllm/v1/ + commands: + - export VLLM_WORKER_MULTIPROC_METHOD=spawn + - pytest -v -s v1/sample + +- label: ":amd: (MI355 DPX) V1 Logits + Oracle" + timeout_in_minutes: 70 + mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] + dind: false + agent_pool: mi355_dpx + optional: true + working_dir: /vllm-workspace/tests + source_file_dependencies: + - vllm/ + - tests/v1/sample + - tests/v1/logits_processors + - tests/v1/test_oracle.py + - tests/v1/test_request.py + - tests/v1/test_outputs.py + - vllm/config/ + - vllm/distributed/ + - vllm/engine/ + - vllm/inputs/ + - vllm/logger.py + - vllm/model_executor/ + - vllm/platforms/ + - vllm/sampling_params.py + - vllm/transformers_utils/ + - vllm/utils/ + - vllm/v1/ + commands: + - export VLLM_WORKER_MULTIPROC_METHOD=spawn + - pytest -v -s v1/logits_processors + - pytest -v -s v1/test_oracle.py + - pytest -v -s v1/test_request.py + - pytest -v -s v1/test_outputs.py + + +- label: ":amd: (MI355 DPX) E2E Core Large Memory" + timeout_in_minutes: 65 + mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] + dind: false + agent_pool: mi355_dpx num_gpus: 1 optional: true working_dir: "/vllm-workspace/tests" @@ -5013,11 +5013,11 @@ steps: - pytest -v -s v1/e2e/general/test_kv_sharing_fast_prefill.py - pytest -v -s v1/e2e/general/test_mamba_prefix_cache.py::test_mamba_prefix_cache_mrv2 v1/e2e/general/test_mamba_prefix_cache.py::test_mamba_prefix_cache_mrv2_async -- label: ":amd: (MI355) Extract Hidden States Integration Single GPU" +- label: ":amd: (MI355 DPX) Extract Hidden States Integration Single GPU" timeout_in_minutes: 45 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] dind: false - agent_pool: mi355_1 + agent_pool: mi355_dpx num_gpus: 1 optional: true working_dir: "/vllm-workspace" @@ -5032,11 +5032,11 @@ steps: - export VLLM_WORKER_MULTIPROC_METHOD=spawn - pytest -v -s -m 'not distributed' tests/v1/kv_connector/extract_hidden_states_integration -- label: ":amd: (MI355) V1 Attention Shard %N" # TBD +- label: ":amd: (MI355 DPX) V1 Attention Shard %N" # TBD timeout_in_minutes: 125 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] dind: false - agent_pool: mi355_1 + agent_pool: mi355_dpx parallelism: 2 working_dir: "/vllm-workspace/tests" source_file_dependencies: @@ -5051,11 +5051,11 @@ steps: commands: - pytest -v -s v1/attention --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT -- label: ":amd: (MI355) V1 Core" +- label: ":amd: (MI355 DPX) V1 Core (MI355 suite)" timeout_in_minutes: 60 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] dind: false - agent_pool: mi355_1 + agent_pool: mi355_dpx optional: true working_dir: "/vllm-workspace/tests" source_file_dependencies: @@ -5092,11 +5092,11 @@ steps: - export VLLM_WORKER_MULTIPROC_METHOD=spawn - pytest -v -s -m 'not cpu_test' v1/core -- label: ":amd: (MI355) V1 Executor + Worker" +- label: ":amd: (MI355 DPX) V1 Executor + Worker (MI355 suite)" timeout_in_minutes: 60 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] dind: false - agent_pool: mi355_1 + agent_pool: mi355_dpx optional: true working_dir: /vllm-workspace/tests source_file_dependencies: @@ -5135,11 +5135,11 @@ steps: - pytest -v -s v1/worker - pytest -v -s v1/streaming_input -- label: ":amd: (MI355) V1 KV Offload" +- label: ":amd: (MI355 DPX) V1 KV Offload (MI355 suite)" timeout_in_minutes: 60 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] dind: false - agent_pool: mi355_1 + agent_pool: mi355_dpx optional: true working_dir: /vllm-workspace/tests source_file_dependencies: @@ -5178,12 +5178,12 @@ steps: - pytest -v -s v1/kv_offload - pytest -v -s v1/simple_kv_offload -- label: ":amd: (MI355) V1 KV Connectors Shard %N" +- label: ":amd: (MI355 DPX) V1 KV Connectors Shard %N (MI355 suite)" timeout_in_minutes: 60 parallelism: 4 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] dind: false - agent_pool: mi355_1 + agent_pool: mi355_dpx optional: true working_dir: /vllm-workspace/tests source_file_dependencies: @@ -5222,11 +5222,11 @@ steps: - pytest -v -s -m 'not cpu_test' v1/kv_connector/unit --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB - pytest -v -s -m 'not cpu_test' v1/ec_connector/unit --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB -- label: ":amd: (MI355) V1 Metrics + LM Eval" +- label: ":amd: (MI355 DPX) V1 Metrics + LM Eval (MI355 suite)" timeout_in_minutes: 65 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] dind: false - agent_pool: mi355_1 + agent_pool: mi355_dpx optional: true working_dir: /vllm-workspace/tests source_file_dependencies: @@ -5269,11 +5269,11 @@ steps: - pip install -U git+https://github.com/vllm-project/lm-evaluation-harness.git@streaming-api - pytest -v -s entrypoints/openai/correctness/test_lmeval.py::test_lm_eval_accuracy_v1_engine -- label: ":amd: (MI355) CUDAGraph" +- label: ":amd: (MI355 DPX) CUDAGraph" timeout_in_minutes: 55 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] dind: false - agent_pool: mi355_1 + agent_pool: mi355_dpx optional: true working_dir: /vllm-workspace/tests source_file_dependencies: @@ -5299,11 +5299,11 @@ steps: - pytest -v -s v1/cudagraph/test_encoder_cudagraph.py -- label: ":amd: (MI355) V1 Sample" +- label: ":amd: (MI355 DPX) V1 Sample (MI355 suite)" timeout_in_minutes: 70 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] dind: false - agent_pool: mi355_1 + agent_pool: mi355_dpx optional: true working_dir: "/vllm-workspace/tests" source_file_dependencies: @@ -5328,11 +5328,11 @@ steps: - export VLLM_WORKER_MULTIPROC_METHOD=spawn - pytest -v -s v1/sample -- label: ":amd: (MI355) V1 Logits + Oracle" +- label: ":amd: (MI355 DPX) V1 Logits + Oracle (MI355 suite)" timeout_in_minutes: 70 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] dind: false - agent_pool: mi355_1 + agent_pool: mi355_dpx optional: true working_dir: /vllm-workspace/tests source_file_dependencies: @@ -5385,12 +5385,12 @@ steps: - export VLLM_WORKER_MULTIPROC_METHOD=spawn - pytest -v -s -m 'not slow_test' v1/spec_decode -- label: ":amd: (MI355) Spec Decode AL MTP + Other Acceptance Nightly" +- label: ":amd: (MI355 DPX) Spec Decode AL MTP + Other Acceptance Nightly" timeout_in_minutes: 55 parallelism: 3 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] dind: false - agent_pool: mi355_1 + agent_pool: mi355_dpx optional: true working_dir: "/vllm-workspace/tests" source_file_dependencies: @@ -5420,11 +5420,11 @@ steps: #----------------------------------------------------------- mi355 · misc ------------------------------------------------------------# -- label: ":amd: (MI355) Regression" # TBD +- label: ":amd: (MI355 DPX) Regression" # TBD timeout_in_minutes: 25 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] dind: false - agent_pool: mi355_1 + agent_pool: mi355_dpx optional: true working_dir: "/vllm-workspace/tests" source_file_dependencies: diff --git a/.buildkite/test_areas/basic_correctness.yaml b/.buildkite/test_areas/basic_correctness.yaml index 43e3113eb3..eadcf2e237 100644 --- a/.buildkite/test_areas/basic_correctness.yaml +++ b/.buildkite/test_areas/basic_correctness.yaml @@ -19,9 +19,9 @@ steps: - pytest -v -s basic_correctness/test_cpu_offload.py mirror: amd: - label: ":amd: (MI300) Basic Correctness" + label: ":amd: (MI355 DPX) Basic Correctness" dind: false - device: mi300_1 + device: mi355_dpx timeout_in_minutes: 60 depends_on: - image-build-amd diff --git a/.buildkite/test_areas/benchmarks.yaml b/.buildkite/test_areas/benchmarks.yaml index bfa86e5597..4b681cd589 100644 --- a/.buildkite/test_areas/benchmarks.yaml +++ b/.buildkite/test_areas/benchmarks.yaml @@ -15,9 +15,9 @@ steps: - pytest -v -s benchmarks/ mirror: amd: - label: ":amd: (MI300) Benchmarks CLI" + label: ":amd: (MI355 DPX) Benchmarks CLI" dind: false - device: mi300_1 + device: mi355_dpx timeout_in_minutes: 40 depends_on: - image-build-amd diff --git a/.buildkite/test_areas/compile.yaml b/.buildkite/test_areas/compile.yaml index 2f314aa138..221c2e8838 100644 --- a/.buildkite/test_areas/compile.yaml +++ b/.buildkite/test_areas/compile.yaml @@ -113,9 +113,9 @@ steps: - pytest -v -s tests/compile/fusions_e2e/test_tp1_quant.py -k "inductor_partition and not +rms_norm and +quant_fp8 and (qwen3 or deepseek)" mirror: amd: - label: ":amd: (MI355) Fusion E2E Quick" + label: ":amd: (MI355 DPX) Fusion E2E Quick" dind: false - device: mi355_1 + device: mi355_dpx working_dir: "/vllm-workspace/" timeout_in_minutes: 30 depends_on: @@ -154,9 +154,9 @@ steps: - pytest -v -s tests/compile/fusions_e2e/test_tp1_quant.py -k "llama-3" mirror: amd: - label: ":amd: (MI355) Fusion E2E Config Sweep" + label: ":amd: (MI355 DPX) Fusion E2E Config Sweep" dind: false - device: mi355_1 + device: mi355_dpx working_dir: "/vllm-workspace/" timeout_in_minutes: 40 depends_on: diff --git a/.buildkite/test_areas/cuda.yaml b/.buildkite/test_areas/cuda.yaml index 8ac8e1960a..02ac11879f 100644 --- a/.buildkite/test_areas/cuda.yaml +++ b/.buildkite/test_areas/cuda.yaml @@ -19,9 +19,9 @@ steps: - pytest -v -s cuda/test_cuda_compatibility_path.py mirror: amd: - label: ":amd: (MI355) CUDA Platform" + label: ":amd: (MI355 DPX) CUDA Platform" dind: false - device: mi355_1 + device: mi355_dpx working_dir: "/vllm-workspace/tests" timeout_in_minutes: 25 depends_on: diff --git a/.buildkite/test_areas/disaggregated.yaml b/.buildkite/test_areas/disaggregated.yaml index c8ba471ebd..43abe2ce01 100644 --- a/.buildkite/test_areas/disaggregated.yaml +++ b/.buildkite/test_areas/disaggregated.yaml @@ -153,7 +153,7 @@ steps: label: ":amd: (MI300) Hybrid SSM NixlConnector PD accuracy" dind: false device: mi300_4 - timeout_in_minutes: 60 + timeout_in_minutes: 80 depends_on: - image-build-amd source_file_dependencies: diff --git a/.buildkite/test_areas/distributed.yaml b/.buildkite/test_areas/distributed.yaml index 15966f8bd1..d5673a6c47 100644 --- a/.buildkite/test_areas/distributed.yaml +++ b/.buildkite/test_areas/distributed.yaml @@ -35,9 +35,9 @@ steps: - pytest -v -s distributed/test_sharded_rdt_trainer.py mirror: amd: - label: ":amd: (MI355) Sharded RDT Weight Transfer" + label: ":amd: (MI355 DPX) Sharded RDT Weight Transfer" dind: false - device: mi355_1 + device: mi355_dpx num_devices: 1 timeout_in_minutes: 45 working_dir: /vllm-workspace/tests @@ -224,7 +224,7 @@ steps: label: ":amd: (MI355) Distributed Torchrun + Examples" dind: false device: mi355_4 - timeout_in_minutes: 45 + timeout_in_minutes: 55 depends_on: - image-build-amd source_file_dependencies: diff --git a/.buildkite/test_areas/e2e_integration.yaml b/.buildkite/test_areas/e2e_integration.yaml index 12ebee8930..9af5423a4b 100644 --- a/.buildkite/test_areas/e2e_integration.yaml +++ b/.buildkite/test_areas/e2e_integration.yaml @@ -132,9 +132,9 @@ steps: - bash .buildkite/scripts/scheduled_integration_test/deepseek_v2_lite_prefetch_offload.sh 0.25 200 8030 mirror: amd: - label: ":amd: (MI355) DeepSeek V2-Lite Prefetch Offload Accuracy" + label: ":amd: (MI355 DPX) DeepSeek V2-Lite Prefetch Offload Accuracy" dind: false - device: mi355_1 + device: mi355_dpx working_dir: "/vllm-workspace" timeout_in_minutes: 30 depends_on: diff --git a/.buildkite/test_areas/engine.yaml b/.buildkite/test_areas/engine.yaml index e38cd92573..da02f47827 100644 --- a/.buildkite/test_areas/engine.yaml +++ b/.buildkite/test_areas/engine.yaml @@ -29,9 +29,9 @@ steps: - pytest -v -s engine test_sequence.py test_config.py test_logger.py test_vllm_port.py jit_monitor/test_hooks.py jit_monitor/test_hooks_gpu.py mirror: amd: - label: ":amd: (MI300) Engine Core" + label: ":amd: (MI355 DPX) Engine Core" dind: false - device: mi300_1 + device: mi355_dpx timeout_in_minutes: 40 depends_on: - image-build-amd @@ -117,9 +117,9 @@ steps: - pytest -v -s v1/e2e/general/test_mamba_prefix_cache.py::test_mamba_prefix_cache_mrv2 v1/e2e/general/test_mamba_prefix_cache.py::test_mamba_prefix_cache_mrv2_async mirror: amd: - label: ":amd: (MI355) E2E Core Large Memory" + label: ":amd: (MI355 DPX) E2E Core Large Memory" dind: false - device: mi355_1 + device: mi355_dpx num_devices: 1 timeout_in_minutes: 65 working_dir: /vllm-workspace/tests diff --git a/.buildkite/test_areas/entrypoints.yaml b/.buildkite/test_areas/entrypoints.yaml index 075b3733ca..5f8e1d1c35 100644 --- a/.buildkite/test_areas/entrypoints.yaml +++ b/.buildkite/test_areas/entrypoints.yaml @@ -39,9 +39,9 @@ steps: - pytest -v -s entrypoints/launchers mirror: amd: - label: ":amd: (MI355) Entrypoints Unit" + label: ":amd: (MI355 DPX) Entrypoints Unit" dind: false - device: mi355_1 + device: mi355_dpx timeout_in_minutes: 50 depends_on: - image-build-amd @@ -64,9 +64,9 @@ steps: - pytest -v -s entrypoints/llm/offline_mode # Needs to avoid interference with other tests mirror: amd: - label: ":amd: (MI300) Entrypoints Integration (LLM)" + label: ":amd: (MI355 DPX) Entrypoints Integration (LLM)" dind: false - device: mi300_1 + device: mi355_dpx timeout_in_minutes: 90 depends_on: - image-build-amd @@ -89,9 +89,9 @@ steps: - pytest -v -s entrypoints/scale_out --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB mirror: amd: - label: ":amd: (MI300) Entrypoints Integration (API Server) %N" + label: ":amd: (MI355 DPX) Entrypoints Integration (API Server) %N" dind: false - device: mi300_1 + device: mi355_dpx timeout_in_minutes: 65 depends_on: - image-build-amd @@ -111,9 +111,9 @@ steps: - pytest -v -s entrypoints/openai --ignore=entrypoints/openai/completion --ignore=entrypoints/openai/chat_completion --ignore=entrypoints/openai/responses --ignore=entrypoints/openai/correctness mirror: amd: - label: ":amd: (MI300) Entrypoints Integration (OpenAI API completion)" + label: ":amd: (MI355 DPX) Entrypoints Integration (OpenAI API completion)" dind: false - device: mi300_1 + device: mi355_dpx timeout_in_minutes: 65 depends_on: - image-build-amd @@ -132,9 +132,9 @@ steps: - pytest -v -s entrypoints/openai/chat_completion mirror: amd: - label: ":amd: (MI300) Entrypoints Integration (OpenAI API chat_completion)" + label: ":amd: (MI355 DPX) Entrypoints Integration (OpenAI API chat_completion)" dind: false - device: mi300_1 + device: mi355_dpx timeout_in_minutes: 70 depends_on: - image-build-amd @@ -160,9 +160,9 @@ steps: - pytest -v -s entrypoints/cohere mirror: amd: - label: ":amd: (MI300) Entrypoints Integration (API Server Generate)" + label: ":amd: (MI355 DPX) Entrypoints Integration (API Server Generate)" dind: false - device: mi300_1 + device: mi355_dpx timeout_in_minutes: 65 depends_on: - image-build-amd @@ -180,9 +180,9 @@ steps: - pytest -v -s entrypoints/openai/responses mirror: amd: - label: ":amd: (MI355) Entrypoints Integration (Responses API)" + label: ":amd: (MI355 DPX) Entrypoints Integration (Responses API)" dind: false - device: mi355_1 + device: mi355_dpx timeout_in_minutes: 50 depends_on: - image-build-amd @@ -201,9 +201,9 @@ steps: - pytest -v -s entrypoints/speech_to_text mirror: amd: - label: ":amd: (MI355) Entrypoints Integration (Speech to Text)" + label: ":amd: (MI355 DPX) Entrypoints Integration (Speech to Text)" dind: false - device: mi355_1 + device: mi355_dpx timeout_in_minutes: 60 working_dir: "/vllm-workspace/tests" depends_on: @@ -223,9 +223,9 @@ steps: - pytest -v -s entrypoints/multimodal mirror: amd: - label: ":amd: (MI355) Entrypoints Integration (Multimodal)" + label: ":amd: (MI355 DPX) Entrypoints Integration (Multimodal)" dind: false - device: mi355_1 + device: mi355_dpx timeout_in_minutes: 55 depends_on: - image-build-amd @@ -244,9 +244,9 @@ steps: - pytest -v -s entrypoints/pooling mirror: amd: - label: ":amd: (MI355) Entrypoints Integration (Pooling)" + label: ":amd: (MI355 DPX) Entrypoints Integration (Pooling)" dind: false - device: mi355_1 + device: mi355_dpx timeout_in_minutes: 65 working_dir: "/vllm-workspace/tests" depends_on: @@ -263,9 +263,9 @@ steps: - pytest -s entrypoints/openai/correctness/ mirror: amd: - label: ":amd: (MI300) OpenAI API Correctness" + label: ":amd: (MI355 DPX) OpenAI API Correctness" dind: false - device: mi300_1 + device: mi355_dpx timeout_in_minutes: 30 depends_on: - image-build-amd diff --git a/.buildkite/test_areas/expert_parallelism.yaml b/.buildkite/test_areas/expert_parallelism.yaml index b9ce4f5924..b64eaec3b0 100644 --- a/.buildkite/test_areas/expert_parallelism.yaml +++ b/.buildkite/test_areas/expert_parallelism.yaml @@ -16,9 +16,9 @@ steps: - pytest -v -s distributed/test_eplb_utils.py mirror: amd: - label: ":amd: (MI300) EPLB Algorithm" + label: ":amd: (MI355 DPX) EPLB Algorithm" dind: false - device: mi300_1 + device: mi355_dpx timeout_in_minutes: 30 depends_on: - image-build-amd diff --git a/.buildkite/test_areas/kernels.yaml b/.buildkite/test_areas/kernels.yaml index 8e5b733283..b44d05f2cf 100644 --- a/.buildkite/test_areas/kernels.yaml +++ b/.buildkite/test_areas/kernels.yaml @@ -15,9 +15,9 @@ steps: - pytest -v -s tests/kernels/ir mirror: amd: - label: ":amd: (MI355) vLLM IR" + label: ":amd: (MI355 DPX) vLLM IR" dind: false - device: mi355_1 + device: mi355_dpx timeout_in_minutes: 50 working_dir: "/vllm-workspace/" depends_on: @@ -44,9 +44,9 @@ steps: parallelism: 3 mirror: amd: - label: ":amd: (MI355) Core Operation Kernels Shard %N" + label: ":amd: (MI300) Core Operation Kernels Shard %N" dind: false - device: mi355_1 + device: mi300_1 timeout_in_minutes: 40 working_dir: "/vllm-workspace/tests" depends_on: @@ -113,9 +113,9 @@ steps: - pytest -v -s kernels/test_top_k_per_row.py mirror: amd: - label: ":amd: (MI355) DeepSeek V4 Fused Kernels" + label: ":amd: (MI355 DPX) DeepSeek V4 Fused Kernels" dind: false - device: mi355_1 + device: mi355_dpx num_devices: 1 timeout_in_minutes: 60 working_dir: /vllm-workspace/tests @@ -230,9 +230,9 @@ steps: - pytest -v -s kernels/attention/test_triton_unified_attention_diffkv.py mirror: amd: - label: ":amd: (MI355) Attention DiffKV Kernels" + label: ":amd: (MI355 DPX) Attention DiffKV Kernels" dind: false - device: mi355_1 + device: mi355_dpx num_devices: 1 timeout_in_minutes: 35 working_dir: /vllm-workspace/tests @@ -270,9 +270,9 @@ steps: - pytest -v -s kernels/attention/test_mla_cross_layer_kernel_equivalence.py mirror: amd: - label: ":amd: (MI355) MLA Kernels" + label: ":amd: (MI355 DPX) MLA Kernels" dind: false - device: mi355_1 + device: mi355_dpx num_devices: 1 timeout_in_minutes: 40 working_dir: /vllm-workspace/ @@ -768,10 +768,66 @@ steps: - amd-smi - VLLM_ROCM_USE_AITER=1 VLLM_ROCM_USE_AITER_MOE=1 VLLM_ROCM_USE_AITER_FUSION_SHARED_EXPERTS=0 pytest -v -s kernels/moe/test_mori_moe.py -- label: ":amd: (MI355) FP8 MoE Kernels" +- label: ":amd: (MI355 DPX) Native Quantization Kernels" + key: amd-native-quantization-kernels-mi355 + dind: false + device: mi355_dpx + num_devices: 1 + timeout_in_minutes: 40 + working_dir: /vllm-workspace/tests + depends_on: + - image-build-amd + source_file_dependencies: + - csrc/rocm/ + - vllm/model_executor/layers/quantization/ + - vllm/model_executor/kernels/linear/ + - vllm/_aiter_ops.py + - vllm/_custom_ops.py + - vllm/platforms/rocm.py + - vllm/envs.py + - tests/kernels/quantization/test_rocm_mxfp4.py + - tests/kernels/quantization/test_rocm_mxfp8_linear.py + - tests/kernels/quantization/test_rocm_skinny_gemms.py + - tests/quantization/reference_mxfp4.py + - tests/kernels/quant_utils.py + - tests/kernels/utils.py + commands: + - pytest -v -s kernels/quantization/test_rocm_mxfp4.py + - pytest -v -s kernels/quantization/test_rocm_mxfp8_linear.py + - pytest -v -s kernels/quantization/test_rocm_skinny_gemms.py -k wvsplitkrc + +- label: ":amd: (MI355 DPX) FP4 and INT4 MoE Kernels" + key: amd-fp4-moe-kernels-mi355 + dind: false + device: mi355_dpx + num_devices: 1 + timeout_in_minutes: 40 + working_dir: /vllm-workspace/tests + depends_on: + - image-build-amd + source_file_dependencies: + - csrc/moe/ + - csrc/rocm/ + - vllm/model_executor/layers/fused_moe/ + - vllm/model_executor/layers/quantization/ + - vllm/_aiter_ops.py + - vllm/platforms/rocm.py + - vllm/envs.py + - vllm/config/ + - tests/kernels/moe/test_rocm_aiter_moe.py + - tests/kernels/moe/test_ocp_mx_moe.py + - tests/kernels/moe/test_flydsl_moe.py + - tests/kernels/moe/utils.py + - tests/kernels/utils.py + commands: + - pytest -v -s kernels/moe/test_rocm_aiter_moe.py -k 'mi350_mxfp4 or quant_scheme_support_matches_gfx950' + - pytest -v -s kernels/moe/test_ocp_mx_moe.py::test_rocm_mxfp4_moe_oracle -k AITER_MXFP4 + - pytest -v -s kernels/moe/test_flydsl_moe.py + +- label: ":amd: (MI355 DPX) FP8 MoE Kernels" key: amd-fp8-moe-kernels-mi355 dind: false - device: mi355_1 + device: mi355_dpx num_devices: 1 timeout_in_minutes: 40 working_dir: /vllm-workspace/tests @@ -798,10 +854,10 @@ steps: - pytest -v -s kernels/moe/test_triton_moe_no_act_mul.py - pytest -v -s kernels/moe/test_triton_moe_ptpc_fp8.py -- label: ":amd: (MI355) Kernels" +- label: ":amd: (MI355 DPX) Kernels" key: amd-kernels-mi355 dind: false - device: mi355_1 + device: mi355_dpx num_devices: 1 timeout_in_minutes: 25 working_dir: /vllm-workspace/ diff --git a/.buildkite/test_areas/lm_eval.yaml b/.buildkite/test_areas/lm_eval.yaml index e93157e521..c67cc08b94 100644 --- a/.buildkite/test_areas/lm_eval.yaml +++ b/.buildkite/test_areas/lm_eval.yaml @@ -68,9 +68,9 @@ steps: - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-watermark.txt mirror: amd: - label: ":amd: (MI355) LM Eval Watermarking" + label: ":amd: (MI355 DPX) LM Eval Watermarking" dind: false - device: mi355_1 + device: mi355_dpx num_devices: 1 timeout_in_minutes: 45 working_dir: /vllm-workspace/tests @@ -146,6 +146,28 @@ steps: - vllm/model_executor/layers/quantization commands: - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-blackwell.txt + mirror: + amd: + label: ":amd: (MI355 DPX) LM Eval Small Models" + dind: false + device: mi355_dpx + timeout_in_minutes: 45 + working_dir: /vllm-workspace/tests + depends_on: + - image-build-amd + source_file_dependencies: + - csrc/ + - tests/evals/gsm8k/ + - vllm/model_executor/layers/quantization + - vllm/model_executor/kernels/linear/ + - vllm/model_executor/models/ + - vllm/model_executor/model_loader/ + - vllm/v1/attention/backends/ + - vllm/v1/attention/selector.py + - vllm/_aiter_ops.py + - vllm/platforms/rocm.py + commands: + - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-gfx950-small.txt - label: ":nvidia: (B200) LM Eval Small Models Distributed" key: lm-eval-small-models-distributed-2xb200 @@ -972,9 +994,9 @@ steps: - pytest -s -v evals/mrcr/test_mrcr_correctness.py --config-list-file=evals/mrcr/configs/models-small.txt mirror: amd: - label: ":amd: (MI355) MRCR Eval Small Models" + label: ":amd: (MI355 DPX) MRCR Eval Small Models" dind: false - device: mi355_1 + device: mi355_dpx timeout_in_minutes: 40 depends_on: - image-build-amd diff --git a/.buildkite/test_areas/lora.yaml b/.buildkite/test_areas/lora.yaml index 28f695f391..8321bc7a4f 100644 --- a/.buildkite/test_areas/lora.yaml +++ b/.buildkite/test_areas/lora.yaml @@ -14,9 +14,9 @@ steps: parallelism: 4 mirror: amd: - label: ":amd: (MI300) LoRA Shard %N" + label: ":amd: (MI355 DPX) LoRA Shard %N" dind: false - device: mi300_1 + device: mi355_dpx working_dir: "/vllm-workspace/tests" timeout_in_minutes: 85 source_file_dependencies: diff --git a/.buildkite/test_areas/misc.yaml b/.buildkite/test_areas/misc.yaml index ad1c58f087..0aede333e3 100644 --- a/.buildkite/test_areas/misc.yaml +++ b/.buildkite/test_areas/misc.yaml @@ -29,9 +29,9 @@ steps: - pytest -v -s v1/sample mirror: amd: - label: ":amd: (MI300) V1 Sample" + label: ":amd: (MI355 DPX) V1 Sample" dind: false - device: mi300_1 + device: mi355_dpx timeout_in_minutes: 70 depends_on: - image-build-amd @@ -51,9 +51,9 @@ steps: - pytest -v -s v1/test_outputs.py mirror: amd: - label: ":amd: (MI300) V1 Logits + Oracle" + label: ":amd: (MI355 DPX) V1 Logits + Oracle" dind: false - device: mi300_1 + device: mi355_dpx timeout_in_minutes: 70 depends_on: - image-build-amd @@ -96,9 +96,9 @@ steps: - pytest -v -s -m 'not cpu_test' v1/core mirror: amd: - label: ":amd: (MI300) V1 Core" + label: ":amd: (MI355 DPX) V1 Core" dind: false - device: mi300_1 + device: mi355_dpx timeout_in_minutes: 60 depends_on: - image-build-amd @@ -116,9 +116,9 @@ steps: - pytest -v -s v1/streaming_input mirror: amd: - label: ":amd: (MI300) V1 Executor + Worker" + label: ":amd: (MI355 DPX) V1 Executor + Worker" dind: false - device: mi300_1 + device: mi355_dpx timeout_in_minutes: 60 depends_on: - image-build-amd @@ -135,9 +135,9 @@ steps: - pytest -v -s v1/simple_kv_offload mirror: amd: - label: ":amd: (MI300) V1 KV Offload" + label: ":amd: (MI355 DPX) V1 KV Offload" dind: false - device: mi300_1 + device: mi355_dpx timeout_in_minutes: 60 depends_on: - image-build-amd @@ -155,9 +155,9 @@ steps: - pytest -v -s -m 'not cpu_test' v1/ec_connector/unit --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB mirror: amd: - label: ":amd: (MI300) V1 KV Connectors Shard %N" + label: ":amd: (MI355 DPX) V1 KV Connectors Shard %N" dind: false - device: mi300_1 + device: mi355_dpx timeout_in_minutes: 60 depends_on: - image-build-amd @@ -182,9 +182,9 @@ steps: - pytest -v -s entrypoints/openai/correctness/test_lmeval.py::test_lm_eval_accuracy_v1_engine mirror: amd: - label: ":amd: (MI300) V1 Metrics + LM Eval" + label: ":amd: (MI355 DPX) V1 Metrics + LM Eval" dind: false - device: mi300_1 + device: mi355_dpx timeout_in_minutes: 65 depends_on: - image-build-amd @@ -239,9 +239,9 @@ steps: - pytest -v -s tests/v1/kv_connector/extract_hidden_states_integration mirror: amd: - label: ":amd: (MI355) Extract Hidden States Integration Single GPU" + label: ":amd: (MI355 DPX) Extract Hidden States Integration Single GPU" dind: false - device: mi355_1 + device: mi355_dpx num_devices: 1 timeout_in_minutes: 45 working_dir: /vllm-workspace @@ -328,9 +328,9 @@ steps: working_dir: "/vllm-workspace/tests" # optional mirror: amd: - label: ":amd: (MI355) Regression" + label: ":amd: (MI355 DPX) Regression" dind: false - device: mi355_1 + device: mi355_dpx timeout_in_minutes: 25 depends_on: - image-build-amd @@ -370,9 +370,9 @@ steps: - python3 features/speculative_decoding/spec_decode_offline.py --test --method eagle3 --num_spec_tokens 3 --dataset-name hf --dataset-path philschmid/mt-bench --num-prompts 80 --temp 0 --top-p 1.0 --top-k -1 --tp 1 --enable-chunked-prefill --max-model-len 1536 mirror: amd: - label: ":amd: (MI300) Examples" + label: ":amd: (MI355 DPX) Examples" dind: false - device: mi300_1 + device: mi355_dpx timeout_in_minutes: 75 source_file_dependencies: - vllm/entrypoints @@ -472,9 +472,9 @@ steps: - pytest -v -s utils_ mirror: amd: - label: ":amd: (MI355) Async Engine, Inputs, Utils, Worker" + label: ":amd: (MI355 DPX) Async Engine, Inputs, Utils, Worker" dind: false - device: mi355_1 + device: mi355_dpx timeout_in_minutes: 50 depends_on: - image-build-amd @@ -667,9 +667,9 @@ steps: - pytest -v -s v1/spec_decode/test_acceptance_length.py -m slow_test mirror: amd: - label: ":amd: (MI355) Acceptance Length (Large Models)" + label: ":amd: (MI355 DPX) Acceptance Length (Large Models)" dind: false - device: mi355_1 + device: mi355_dpx timeout_in_minutes: 45 depends_on: - image-build-amd diff --git a/.buildkite/test_areas/models_basic.yaml b/.buildkite/test_areas/models_basic.yaml index cb9e25c0f9..83a08cfc24 100644 --- a/.buildkite/test_areas/models_basic.yaml +++ b/.buildkite/test_areas/models_basic.yaml @@ -16,9 +16,9 @@ steps: - pytest -v -s models/test_initialization.py::test_can_initialize_small_subset mirror: amd: - label: ":amd: (MI355) Basic Models (Initialization)" + label: ":amd: (MI355 DPX) Basic Models (Initialization)" dind: false - device: mi355_1 + device: mi355_dpx timeout_in_minutes: 30 depends_on: - image-build-amd @@ -39,9 +39,9 @@ steps: parallelism: 14 mirror: amd: - label: ":amd: (MI355) Basic Models (Extra Initialization) Shard %N" + label: ":amd: (MI355 DPX) Basic Models (Extra Initialization) Shard %N" dind: false - device: mi355_1 + device: mi355_dpx timeout_in_minutes: 60 parallelism: 10 working_dir: "/vllm-workspace/tests" @@ -70,9 +70,9 @@ steps: - pytest -v -s models/test_terratorch.py models/transformers/test_backend.py models/test_registry.py models/test_deepseek_v4_vl_rocm.py mirror: amd: - label: ":amd: (MI300) Basic Models (Other)" + label: ":amd: (MI355 DPX) Basic Models (Other)" dind: false - device: mi300_1 + device: mi355_dpx timeout_in_minutes: 65 depends_on: - image-build-amd @@ -138,9 +138,9 @@ steps: - pytest -v -s models/glm5next mirror: amd: - label: ":amd: (MI355) GLM5Next" + label: ":amd: (MI355 DPX) GLM5Next" dind: false - device: mi355_1 + device: mi355_dpx timeout_in_minutes: 35 working_dir: "/vllm-workspace/tests" depends_on: @@ -162,9 +162,9 @@ steps: - pytest -v -s models/qwen4_exp/test_hc_ops.py models/qwen4_exp/test_qsa_pre_indexer.py models/qwen4_exp/test_qsa_reference.py mirror: amd: - label: ":amd: (MI300) Qwen4 Exp" + label: ":amd: (MI355 DPX) Qwen4 Exp" dind: false - device: mi300_1 + device: mi355_dpx depends_on: - image-build-amd commands: diff --git a/.buildkite/test_areas/models_language.yaml b/.buildkite/test_areas/models_language.yaml index c8473e7f0b..fa8013ec54 100644 --- a/.buildkite/test_areas/models_language.yaml +++ b/.buildkite/test_areas/models_language.yaml @@ -16,9 +16,9 @@ steps: - pytest -v -s models/language -m 'core_model and (not slow_test)' mirror: amd: - label: ":amd: (MI300) Language Models (Standard)" + label: ":amd: (MI355 DPX) Language Models (Standard)" dind: false - device: mi300_1 + device: mi355_dpx timeout_in_minutes: 60 depends_on: - image-build-amd @@ -40,9 +40,9 @@ steps: parallelism: 2 mirror: amd: - label: ":amd: (MI300) Language Models (Extra Standard) Shard %N" + label: ":amd: (MI355 DPX) Language Models (Extra Standard) Shard %N" dind: false - device: mi300_1 + device: mi355_dpx timeout_in_minutes: 40 depends_on: - image-build-amd @@ -82,9 +82,9 @@ steps: parallelism: 2 mirror: amd: - label: ":amd: (MI355) Language Models (Hybrid) Shard %N" + label: ":amd: (MI355 DPX) Language Models (Hybrid) Shard %N" dind: false - device: mi355_1 + device: mi355_dpx timeout_in_minutes: 65 depends_on: - image-build-amd @@ -113,9 +113,9 @@ steps: - pytest -v -s models/language/generation -m hybrid_model -k 'granite-4.0-tiny-preview' mirror: amd: - label: ":amd: (MI355) Granite Language Model Compatibility" + label: ":amd: (MI355 DPX) Granite Language Model Compatibility" dind: false - device: mi355_1 + device: mi355_dpx num_devices: 1 timeout_in_minutes: 80 working_dir: /vllm-workspace/tests @@ -151,9 +151,9 @@ steps: - pytest -v -s models/language/generation -m '(not core_model) and (not hybrid_model)' mirror: amd: - label: ":amd: (MI355) Language Models (Extended Generation)" + label: ":amd: (MI355 DPX) Language Models (Extended Generation)" dind: false - device: mi355_1 + device: mi355_dpx timeout_in_minutes: 95 depends_on: - image-build-amd diff --git a/.buildkite/test_areas/models_multimodal.yaml b/.buildkite/test_areas/models_multimodal.yaml index 779801a2ea..e07f38a7bd 100644 --- a/.buildkite/test_areas/models_multimodal.yaml +++ b/.buildkite/test_areas/models_multimodal.yaml @@ -15,9 +15,9 @@ steps: - pytest -v -s models/multimodal/generation/test_ultravox.py -m core_model mirror: amd: - label: ":amd: (MI300) Multimodal Models (Standard) 1: qwen2" + label: ":amd: (MI355 DPX) Multimodal Models (Standard) 1: qwen2" dind: false - device: mi300_1 + device: mi355_dpx timeout_in_minutes: 65 depends_on: - image-build-amd @@ -36,9 +36,9 @@ steps: - pytest -v -s models/multimodal/generation/test_qwen2_5_vl.py -m core_model mirror: amd: - label: ":amd: (MI300) Multimodal Models (Standard) 2: qwen3 + gemma" + label: ":amd: (MI355 DPX) Multimodal Models (Standard) 2: qwen3 + gemma" dind: false - device: mi300_1 + device: mi355_dpx timeout_in_minutes: 55 depends_on: - image-build-amd @@ -78,9 +78,9 @@ steps: - cd .. && VLLM_WORKER_MULTIPROC_METHOD=spawn pytest -v -s tests/models/multimodal/generation/test_whisper.py -m core_model # Otherwise, mp_method="spawn" doesn't work mirror: amd: - label: ":amd: (MI355) Multimodal Models (Standard) 4: other + whisper" + label: ":amd: (MI355 DPX) Multimodal Models (Standard) 4: other + whisper" dind: false - device: mi355_1 + device: mi355_dpx timeout_in_minutes: 70 depends_on: - image-build-amd @@ -125,9 +125,9 @@ steps: - pytest -v -s models/multimodal/processing/test_tensor_schema.py --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB mirror: amd: - label: ":amd: (MI355) Multimodal Processor Shard %N" + label: ":amd: (MI355 DPX) Multimodal Processor Shard %N" dind: false - device: mi355_1 + device: mi355_dpx parallelism: 4 timeout_in_minutes: 115 depends_on: @@ -146,9 +146,9 @@ steps: - pytest -s -v test_lm_eval_correctness.py --config-list-file=configs/models-mm-small.txt --tp-size=1 mirror: amd: - label: ":amd: (MI300) Multimodal Accuracy Eval (Small Models)" + label: ":amd: (MI355 DPX) Multimodal Accuracy Eval (Small Models)" dind: false - device: mi300_1 + device: mi355_dpx timeout_in_minutes: 35 depends_on: - image-build-amd @@ -212,9 +212,9 @@ steps: - pytest -v -s models/multimodal/generation/test_common.py -m 'split(group=0) and not core_model' --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB mirror: amd: - label: ":amd: (MI355) Multimodal Models (Extended Generation 2) Shard %N" + label: ":amd: (MI355 DPX) Multimodal Models (Extended Generation 2) Shard %N" dind: false - device: mi355_1 + device: mi355_dpx timeout_in_minutes: 100 depends_on: - image-build-amd @@ -231,9 +231,9 @@ steps: - pytest -v -s models/multimodal/generation/test_common.py -m 'split(group=1) and not core_model' mirror: amd: - label: ":amd: (MI355) Multimodal Models (Extended Generation 3)" + label: ":amd: (MI355 DPX) Multimodal Models (Extended Generation 3)" dind: false - device: mi355_1 + device: mi355_dpx timeout_in_minutes: 90 depends_on: - image-build-amd diff --git a/.buildkite/test_areas/plugins.yaml b/.buildkite/test_areas/plugins.yaml index 6b901d8f49..d9653e84ee 100644 --- a/.buildkite/test_areas/plugins.yaml +++ b/.buildkite/test_areas/plugins.yaml @@ -78,9 +78,9 @@ steps: - pytest -v -s plugins_tests/gguf mirror: amd: - label: ":amd: (MI355) GGUF Plugin" + label: ":amd: (MI355 DPX) GGUF Plugin" dind: false - device: mi355_1 + device: mi355_dpx timeout_in_minutes: 45 working_dir: "/vllm-workspace/tests" depends_on: diff --git a/.buildkite/test_areas/pytorch.yaml b/.buildkite/test_areas/pytorch.yaml index 8204fb9670..38f0f617bc 100644 --- a/.buildkite/test_areas/pytorch.yaml +++ b/.buildkite/test_areas/pytorch.yaml @@ -89,9 +89,9 @@ steps: - "find compile/h100/ -name 'test_*.py' -print0 | xargs -0 -n1 -I{} pytest -s -v '{}'" mirror: amd: - label: ":amd: (MI355) PyTorch Compilation H100 Cases" + label: ":amd: (MI355 DPX) PyTorch Compilation H100 Cases" dind: false - device: mi355_1 + device: mi355_dpx timeout_in_minutes: 45 working_dir: "/vllm-workspace/tests" depends_on: @@ -192,10 +192,14 @@ steps: - "find compile/fullgraph/ -name 'test_*.py' -not -name 'test_full_cudagraph.py' -print0 | xargs -0 -n1 -I{} pytest -s -v '{}'" mirror: amd: - label: ":amd: (MI355) PyTorch Fullgraph" + label: ":amd: (MI355 DPX) PyTorch Fullgraph" dind: false - device: mi355_1 + device: mi355_dpx timeout_in_minutes: 90 + # Remove once the ROCm Triton pin includes triton-lang/triton#11567. + # Avoid overlapping LLVM codegen/LLD by disabling background precompilation. + env: + TORCHINDUCTOR_PRECOMPILATION_TIMEOUT_SECONDS: "0" depends_on: - image-build-amd diff --git a/.buildkite/test_areas/quantization.yaml b/.buildkite/test_areas/quantization.yaml index f9a4e86e6e..d1f47cf2a7 100644 --- a/.buildkite/test_areas/quantization.yaml +++ b/.buildkite/test_areas/quantization.yaml @@ -22,9 +22,9 @@ steps: - VLLM_TEST_FORCE_LOAD_FORMAT=auto pytest -v -s quantization/ --ignore quantization/test_blackwell_moe.py --ignore quantization/test_rocm_moe.py -k 'not test_compressed_tensors_w4a8_fp8' --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT mirror: amd: - label: ":amd: (MI355) Quantization Shard %N" + label: ":amd: (MI300) Quantization Shard %N" dind: false - device: mi355_1 + device: mi300_1 timeout_in_minutes: 115 working_dir: "/vllm-workspace/tests" depends_on: @@ -116,9 +116,9 @@ steps: - pytest -v -s models/quantization mirror: amd: - label: ":amd: (MI355) Quantized Models" + label: ":amd: (MI355 DPX) Quantized Models" dind: false - device: mi355_1 + device: mi355_dpx timeout_in_minutes: 80 working_dir: "/vllm-workspace/tests" depends_on: diff --git a/.buildkite/test_areas/ray_compat.yaml b/.buildkite/test_areas/ray_compat.yaml index dc8571b260..a177ec7131 100644 --- a/.buildkite/test_areas/ray_compat.yaml +++ b/.buildkite/test_areas/ray_compat.yaml @@ -18,9 +18,9 @@ steps: - bash /vllm-workspace/.buildkite/scripts/check-ray-compatibility.sh mirror: amd: - label: ":amd: (MI355) Ray Dependency Compatibility Check" + label: ":amd: (MI355 DPX) Ray Dependency Compatibility Check" dind: false - device: mi355_1 + device: mi355_dpx timeout_in_minutes: 25 working_dir: "/" depends_on: diff --git a/.buildkite/test_areas/rust_frontend.yaml b/.buildkite/test_areas/rust_frontend.yaml index b8d0e58f58..a3d282864d 100644 --- a/.buildkite/test_areas/rust_frontend.yaml +++ b/.buildkite/test_areas/rust_frontend.yaml @@ -43,9 +43,9 @@ steps: - pytest -v -s v1/sample/test_logprobs_e2e.py -k "test_prompt_logprobs_e2e_server" mirror: amd: - label: ":amd: (MI355) Rust Frontend OpenAI Coverage" + label: ":amd: (MI355 DPX) Rust Frontend OpenAI Coverage" dind: false - device: mi355_1 + device: mi355_dpx timeout_in_minutes: 35 depends_on: - image-build-amd @@ -98,9 +98,9 @@ steps: - pytest -v -s entrypoints/serve/tokenize/test_tokenization.py -k "not tokenizer_info" mirror: amd: - label: ":amd: (MI355) Rust Frontend Serve/Admin Coverage" + label: ":amd: (MI355 DPX) Rust Frontend Serve/Admin Coverage" dind: false - device: mi355_1 + device: mi355_dpx timeout_in_minutes: 30 depends_on: - image-build-amd @@ -133,9 +133,9 @@ steps: - pytest -s entrypoints/openai/correctness/test_lmeval.py::test_lm_eval_accuracy_v1_engine mirror: amd: - label: ":amd: (MI355) Rust Frontend Core Correctness" + label: ":amd: (MI355 DPX) Rust Frontend Core Correctness" dind: false - device: mi355_1 + device: mi355_dpx timeout_in_minutes: 25 depends_on: - image-build-amd @@ -163,9 +163,9 @@ steps: - pytest -v -s tool_use --ignore=tool_use/mistral --models llama3.2 -k "not test_response_format_with_tool_choice_required and not test_parallel_tool_calls_false and not test_tool_call_and_choice" mirror: amd: - label: ":amd: (MI355) Rust Frontend Tool Use" + label: ":amd: (MI355 DPX) Rust Frontend Tool Use" dind: false - device: mi355_1 + device: mi355_dpx timeout_in_minutes: 30 depends_on: - image-build-amd diff --git a/.buildkite/test_areas/samplers.yaml b/.buildkite/test_areas/samplers.yaml index 084583c8a7..bc811883ee 100644 --- a/.buildkite/test_areas/samplers.yaml +++ b/.buildkite/test_areas/samplers.yaml @@ -53,9 +53,9 @@ steps: - VLLM_USE_FLASHINFER_SAMPLER=1 pytest -v -s samplers/test_beam_search.py::test_beam_search_passes_multimodal_data mirror: amd: - label: ":amd: (MI355) Samplers Multimodal Beam Search" + label: ":amd: (MI355 DPX) Samplers Multimodal Beam Search" dind: false - device: mi355_1 + device: mi355_dpx num_devices: 1 timeout_in_minutes: 45 working_dir: /vllm-workspace/tests diff --git a/.buildkite/test_areas/spec_decode.yaml b/.buildkite/test_areas/spec_decode.yaml index 2baeefcc28..8a41a4c993 100644 --- a/.buildkite/test_areas/spec_decode.yaml +++ b/.buildkite/test_areas/spec_decode.yaml @@ -44,9 +44,9 @@ steps: - pytest -v -s v1/e2e/spec_decode/eagle/ -k "deepseek_eagle or qwen3_eagle3" mirror: amd: - label: ":amd: (MI300) Spec Decode Eagle 1: DeepSeek + Qwen" + label: ":amd: (MI355 DPX) Spec Decode Eagle 1: DeepSeek + Qwen" dind: false - device: mi300_1 + device: mi355_dpx timeout_in_minutes: 60 depends_on: - image-build-amd @@ -71,9 +71,9 @@ steps: - pytest -v -s v1/e2e/spec_decode/eagle/ -k "not deepseek_eagle and not qwen3_eagle3" mirror: amd: - label: ":amd: (MI300) Spec Decode Eagle 2: Llama 3 + Qwen VL + Other" + label: ":amd: (MI355 DPX) Spec Decode Eagle 2: Llama 3 + Qwen VL + Other" dind: false - device: mi300_1 + device: mi355_dpx timeout_in_minutes: 60 depends_on: - image-build-amd @@ -157,9 +157,9 @@ steps: - python3 spec_decode/test_custom_proposer.py mirror: amd: - label: ":amd: (MI300) Spec Decode N-Gram + Suffix" + label: ":amd: (MI355 DPX) Spec Decode N-Gram + Suffix" dind: false - device: mi300_1 + device: mi355_dpx timeout_in_minutes: 35 depends_on: - image-build-amd @@ -185,9 +185,9 @@ steps: - pytest -v -s v1/e2e/spec_decode/draft_model/ --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB mirror: amd: - label: ":amd: (MI300) Spec Decode Draft Model Shard %N" + label: ":amd: (MI355 DPX) Spec Decode Draft Model Shard %N" dind: false - device: mi300_1 + device: mi355_dpx timeout_in_minutes: 60 parallelism: 2 depends_on: @@ -392,9 +392,9 @@ steps: - if [ "$$BUILDKITE_PARALLEL_JOB" = "2" ]; then pytest -v -s "v1/e2e/spec_decode/acceptance_rates/mtp_other/test_mtp.py::test_gemma4_mtp_acceptance_lengths[True]"; fi mirror: amd: - label: ":amd: (MI355) Spec Decode AL MTP + Other Acceptance Nightly" + label: ":amd: (MI355 DPX) Spec Decode AL MTP + Other Acceptance Nightly" dind: false - device: mi355_1 + device: mi355_dpx timeout_in_minutes: 55 depends_on: - image-build-amd