From beef814e1d3aa1e198b604a08aa2494fad9842be Mon Sep 17 00:00:00 2001 From: Andreas Karatzas Date: Mon, 28 Sep 2026 15:12:07 -0500 Subject: [PATCH] [ROCm][CI] Add missing test coverage for upstream parity (#50519) Signed-off-by: Andreas Karatzas Signed-off-by: Stefan Koncarevic Signed-off-by: Andreas Karatzas Co-authored-by: Stefan Koncarevic Co-authored-by: OpenAI Codex Co-authored-by: OpenAI Codex --- .buildkite/test-amd.yaml | 440 +++++++++++++++++- .buildkite/test_areas/attention.yaml | 19 + .buildkite/test_areas/disaggregated.yaml | 32 ++ .buildkite/test_areas/kernels.yaml | 29 +- .buildkite/test_areas/lm_eval.yaml | 70 ++- .buildkite/test_areas/models_basic.yaml | 17 + .buildkite/test_areas/quantization.yaml | 16 + .buildkite/test_areas/torch_abi.yaml | 19 + ...ek-V2-Lite-Instruct-FP8-TP1-PCP2-ROCm.yaml | 24 + .../gsm8k/configs/models-qwen35-mi355.txt | 1 + .../gsm8k/configs/models-small-tp-mi355.txt | 2 + 11 files changed, 649 insertions(+), 20 deletions(-) create mode 100644 tests/evals/gsm8k/configs/DeepSeek-V2-Lite-Instruct-FP8-TP1-PCP2-ROCm.yaml create mode 100644 tests/evals/gsm8k/configs/models-small-tp-mi355.txt diff --git a/.buildkite/test-amd.yaml b/.buildkite/test-amd.yaml index 3cc5680ce7..16c1e7075b 100644 --- a/.buildkite/test-amd.yaml +++ b/.buildkite/test-amd.yaml @@ -200,9 +200,9 @@ steps: - pytest -v -s test_sampling_params.py - pytest -v -s -m 'cpu_test' multimodal - pytest -v -s renderers - - pytest -v -s tokenizers_ - pytest -v -s reasoning - pytest -v -s tool_parsers + - pytest -v -s tokenizers_ - pytest -v -s parser - pytest -v -s transformers_utils - pytest -v -s config --ignore=config/test_mp_reducer.py @@ -262,6 +262,24 @@ steps: commands: - pytest -v -s tools/test_docker_build_metadata_args.py +- label: ":amd: (MI250) Torch Stable ABI Audit" # TBD + timeout_in_minutes: 35 + mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] + dind: false + agent_pool: mi300_1 + no_gpu: true + optional: true + working_dir: "/vllm-workspace/" + source_file_dependencies: + - .buildkite/check-torch-abi.py + - csrc/ + - cmake/ + - setup.py + - vllm/platforms/rocm.py + commands: + - uv pip install --system torch-abi-audit==0.0.1 + - python3 /vllm-workspace/.buildkite/check-torch-abi.py + ######################################################################################################################################### # # # MI250 (gfx90a) tests # @@ -415,9 +433,9 @@ steps: - vllm/v1/cudagraph_dispatcher.py - vllm/config/compilation.py - vllm/compilation - - vllm/platforms/rocm.py - vllm/v1/worker/encoder_cudagraph.py - vllm/v1/worker/encoder_cudagraph_defs.py + - vllm/platforms/rocm.py commands: - pytest -v -s v1/cudagraph/test_cudagraph_dispatch.py - pytest -v -s v1/cudagraph/test_cudagraph_mode.py @@ -660,6 +678,8 @@ steps: - "pytest -v -s tests/compile/fusions_e2e/test_tp1_quant.py -k 'inductor_partition and not +rms_norm and not +quant_fp8'" # Different from CUDA, Qwen requires +rms_norm and +quant_fp8 as rms+quant fusion is only supported on AITER - "pytest -v -s tests/compile/fusions_e2e/test_tp1_quant.py -k 'inductor_partition and +rms_norm and +quant_fp8 and qwen3'" + # DeepSeek-Coder uses the portable static-FP8 MLA fusion path on ROCm. + - "pytest -v -s tests/compile/fusions_e2e/test_tp1_quant.py -k 'inductor_partition and not +rms_norm and +quant_fp8 and DeepSeek-Coder and TRITON_MLA and not True'" - label: ":amd: (MI300) PyTorch Compilation Passes" # TBD timeout_in_minutes: 80 @@ -768,7 +788,7 @@ steps: - vllm/platforms/rocm.py commands: - export VLLM_TEST_CLEAN_GPU_MEMORY=1 - - VLLM_TEST_CLEAN_GPU_MEMORY=1 pytest -v -s tests/compile/passes/distributed/test_async_tp.py + - pytest -s -v tests/compile/passes/distributed - pytest -v -s tests/compile/fusions_e2e/test_tp2_ar_rms.py::test_tp2_ar_rms_fusions -k "inductor_partition" - label: ":amd: (MI300) Distributed Compile (Dynamo Partition)" # TBD @@ -790,6 +810,25 @@ steps: - VLLM_TEST_CLEAN_GPU_MEMORY=1 pytest -v -s tests/compile/passes/distributed/test_async_tp.py - pytest -v -s tests/compile/fusions_e2e/test_tp2_ar_rms.py::test_tp2_ar_rms_fusions -k "dynamo_partition" +# - label: ":amd: (MI300) Sequence Parallel Correctness" # TBD +# timeout_in_minutes: 180 +# mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] +# dind: false +# agent_pool: mi300_2 +# num_gpus: 2 +# optional: true +# working_dir: "/vllm-workspace/" +# source_file_dependencies: +# - vllm/model_executor/layers/ +# - vllm/compilation/ +# - vllm/v1/worker/ +# - vllm/v1/cudagraph_dispatcher.py +# - tests/compile/correctness_e2e/test_sequence_parallel.py +# - vllm/platforms/rocm.py +# commands: +# - export VLLM_TEST_CLEAN_GPU_MEMORY=1 +# - pytest -v -s tests/compile/correctness_e2e/test_sequence_parallel.py + - label: ":amd: (MI300) Distributed Compile + RPC" # TBD timeout_in_minutes: 65 mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] @@ -1000,7 +1039,7 @@ steps: - VLLM_ALLOW_INSECURE_SERIALIZATION=1 python3 ../examples/rl/rlhf_http_ipc.py - label: ":amd: (MI300) Elastic EP Scaling" # TBD - timeout_in_minutes: 50 + timeout_in_minutes: 55 mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] dind: false agent_pool: mi300_4 @@ -1015,6 +1054,7 @@ steps: - tests/distributed/ - vllm/platforms/rocm.py commands: + - uv pip install --system -r /vllm-workspace/requirements/kv_connectors_rocm.txt - pytest -v -s distributed/test_elastic_ep.py - label: ":amd: (MI300) RayExecutorV2" # TBD @@ -1248,6 +1288,59 @@ steps: commands: - pytest -s -v evals/mrcr/test_mrcr_correctness.py --config-list-file=evals/mrcr/configs/models-small.txt +- label: ":amd: (MI300) LM Eval KV-Offload" # 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/distributed/kv_transfer/kv_connector/v1/offloading/ + - vllm/distributed/kv_transfer/kv_connector/v1/simple_cpu_offload_connector.py + - vllm/v1/kv_offload/ + - vllm/v1/simple_kv_offload/ + - tests/evals/gsm8k/test_gsm8k_offloading.py + - vllm/platforms/rocm.py + commands: + - pytest -s -v evals/gsm8k/test_gsm8k_offloading.py -k "nemotron-h-8b or gemma-4-e4b-it" + +- label: ":amd: (MI300) LM Eval KV-Offload Medium" # TBD + timeout_in_minutes: 70 + mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] + dind: false + agent_pool: mi300_2 + num_gpus: 2 + optional: true + working_dir: "/vllm-workspace/tests" + source_file_dependencies: + - vllm/distributed/kv_transfer/kv_connector/v1/offloading/ + - vllm/distributed/kv_transfer/kv_connector/v1/simple_cpu_offload_connector.py + - vllm/v1/kv_offload/ + - vllm/v1/simple_kv_offload/ + - tests/evals/gsm8k/test_gsm8k_offloading.py + - vllm/platforms/rocm.py + commands: + - pytest -s -v evals/gsm8k/test_gsm8k_offloading.py -k "qwen3.5-35b or deepseek-v2-lite" + +- label: ":amd: (MI300) LM Eval KV-Offload Large" # TBD + timeout_in_minutes: 65 + mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] + dind: false + agent_pool: mi300_4 + num_gpus: 4 + optional: true + working_dir: "/vllm-workspace/tests" + source_file_dependencies: + - vllm/distributed/kv_transfer/kv_connector/v1/offloading/ + - vllm/distributed/kv_transfer/kv_connector/v1/simple_cpu_offload_connector.py + - vllm/v1/kv_offload/ + - vllm/v1/simple_kv_offload/ + - tests/evals/gsm8k/test_gsm8k_offloading.py + - vllm/platforms/rocm.py + commands: + - VLLM_ROCM_USE_AITER=1 pytest -s -v evals/gsm8k/test_gsm8k_offloading.py -k "deepseek-v4-flash" + - label: ":amd: (MI300) LM Eval Small Models Harness" # TBD timeout_in_minutes: 35 mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] @@ -1399,6 +1492,9 @@ steps: commands: - bash .buildkite/scripts/scheduled_integration_test/qwen30b_a3b_fp8_dp4_async_eplb.sh 0.8 200 8050 +# TODO(akaratza): Retire this standalone ROCm coverage after +# tests/distributed/test_eplb_spec_decode.py is enabled and validated on ROCm. +# The upstream parity job currently skips that entire module on ROCm. - label: ":amd: (MI300) Qwen3-Next-80B-A3B-Instruct MTP Async EPLB Accuracy" # TBD timeout_in_minutes: 45 mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] @@ -1447,7 +1543,7 @@ steps: - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-mi3xx.txt - label: ":amd: (MI300) LM Eval Large Models ROCm Harness" # TBD - timeout_in_minutes: 55 + timeout_in_minutes: 40 mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] dind: false agent_pool: mi300_8 @@ -1466,7 +1562,7 @@ steps: - vllm/platforms/rocm.py commands: - export VLLM_WORKER_MULTIPROC_METHOD=spawn - - pytest -s -v test_lm_eval_correctness.py --config-list-file=configs/models-large-rocm.txt --tp-size=8 + - pytest -s -v test_lm_eval_correctness.py --config-list-file=configs/models-large-rocm.txt --tp-size=8 --timeout=5400 - label: ":amd: (MI300) LM Eval Large Models FP8" # TBD timeout_in_minutes: 40 @@ -1492,7 +1588,7 @@ steps: #---------------------------------------------------------- mi300 · kernels ----------------------------------------------------------# - label: ":amd: (MI300) Core Operation Kernels Shard %N" # TBD - timeout_in_minutes: 40 + timeout_in_minutes: 45 mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] dind: false agent_pool: mi300_1 @@ -1630,8 +1726,8 @@ steps: commands: - pytest -v -s kernels/core/test_minimax_reduce_rms.py -- label: ":amd: (MI300) KDA Kernels" # TBD - timeout_in_minutes: 30 +- label: ":amd: (MI300) Kimi K3" # TBD + timeout_in_minutes: 65 mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] dind: false agent_pool: mi300_1 @@ -1644,11 +1740,20 @@ steps: - vllm/models/kimi_k3/nvidia/kda.py - vllm/models/kimi_k3/nvidia/kda_metadata.py - vllm/models/kimi_k3/nvidia/ops/third_party/kda/ + - vllm/models/kimi_k3/amd/ + - CMakeLists.txt + - csrc/libtorch_stable/kimi_k3/fused_kda_decode_kernel_rocm.cu + - csrc/libtorch_stable/ops.h + - csrc/libtorch_stable/torch_bindings.cpp + - tests/models/kimi_k3/test_amd_attn_res.py + - tests/models/kimi_k3/test_amd_kda_decode.py - tests/models/kimi_k3/test_kda.py - tests/models/kimi_k3/test_kda_metadata.py + - vllm/_custom_ops.py - vllm/platforms/rocm.py commands: - - pytest -v -s models/kimi_k3/test_kda.py models/kimi_k3/test_kda_metadata.py + # Run the ROCm AttnRes/KDA decode counterparts plus existing KDA coverage. + - pytest -v -s models/kimi_k3/test_amd_attn_res.py models/kimi_k3/test_amd_kda_decode.py models/kimi_k3/test_kda.py models/kimi_k3/test_kda_metadata.py - label: ":amd: (MI355) Kimi K3" # TBD timeout_in_minutes: 60 @@ -1782,6 +1887,135 @@ steps: - pytest -v -s model_executor -m '(not slow_test)' --timeout=900 --timeout-method=thread - pytest -v -s entrypoints/openai/completion/test_tensorizer_entrypoint.py --timeout=900 --timeout-method=thread +#---------------------------------------------------- mi300 · model_runner_v2 -------------------------------------------------------# + +- label: ":amd: (MI300) Model Runner V2 Core" # 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/v1/worker/gpu/ + - vllm/v1/worker/gpu_worker.py + - vllm/v1/core/sched/ + - vllm/v1/attention/ + - tests/v1/engine/test_llm_engine.py + - tests/v1/e2e/ + - tests/entrypoints/llm/test_struct_output_generate.py + - vllm/platforms/rocm.py + commands: + - set -x + - export VLLM_USE_V2_MODEL_RUNNER=1 + - pytest -v -s v1/engine/test_llm_engine.py -k "not test_engine_metrics" + - pytest -v -s v1/e2e/general/test_async_scheduling.py -k "not ngram" + - pytest -v -s v1/e2e/general/test_context_length.py + - pytest -v -s v1/e2e/general/test_min_tokens.py + - pytest -v -s entrypoints/llm/test_struct_output_generate.py -k "xgrammar and not speculative_config6 and not speculative_config7 and not speculative_config8 and not speculative_config0" + +- label: ":amd: (MI300) Model Runner V2 Examples" # TBD + timeout_in_minutes: 40 + mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] + dind: false + agent_pool: mi300_1 + optional: true + working_dir: "/vllm-workspace/examples" + source_file_dependencies: + - vllm/v1/worker/gpu/ + - vllm/v1/core/sched/ + - vllm/v1/worker/gpu_worker.py + - examples/basic/offline_inference/ + - examples/generate/multimodal/ + - examples/features/ + - examples/pooling/embed/vision_embedding_offline.py + - examples/features/tensorize_vllm_model.py + - examples/deployment/llm_engine_example.py + - vllm/platforms/rocm.py + commands: + - set -x + - export VLLM_USE_V2_MODEL_RUNNER=1 + - pip install tensorizer + - python3 basic/offline_inference/chat.py + - python3 basic/offline_inference/generate.py --model facebook/opt-125m + - 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: (MI300) Model Runner V2 Distributed" # TBD + timeout_in_minutes: 45 + mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] + dind: false + agent_pool: mi300_2 + num_gpus: 2 + optional: true + working_dir: "/vllm-workspace/tests" + source_file_dependencies: + - vllm/v1/worker/gpu/ + - vllm/v1/worker/gpu_worker.py + - tests/basic_correctness/test_basic_correctness.py + - tests/v1/distributed/test_async_llm_dp.py + - tests/v1/distributed/test_eagle_dp.py + - vllm/platforms/rocm.py + commands: + - set -x + - export VLLM_USE_V2_MODEL_RUNNER=1 + - TARGET_TEST_SUITE=MI300 pytest -v -s basic_correctness/test_basic_correctness.py -m 'distributed(num_gpus=2)' -k "not ray and not True" + - TP_SIZE=1 DP_SIZE=2 pytest -v -s v1/distributed/test_async_llm_dp.py -k "not ray" + - TP_SIZE=1 DP_SIZE=2 pytest -v -s v1/distributed/test_eagle_dp.py + +- label: ":amd: (MI300) Model Runner V2 Pipeline Parallelism" # TBD + timeout_in_minutes: 65 + mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] + dind: false + agent_pool: mi300_4 + num_gpus: 4 + optional: true + working_dir: "/vllm-workspace/tests" + source_file_dependencies: + - vllm/v1/worker/gpu/ + - vllm/v1/worker/gpu_worker.py + - tests/distributed/test_pipeline_parallel.py + - tests/distributed/test_pp_cudagraph.py + - vllm/platforms/rocm.py + commands: + - set -x + - export VLLM_USE_V2_MODEL_RUNNER=1 + - pytest -v -s distributed/test_pipeline_parallel.py -k "not ray" + - pytest -v -s distributed/test_pp_cudagraph.py -k "not ray" + +- label: ":amd: (MI300) Model Runner V2 Spec Decode" # TBD + timeout_in_minutes: 90 + mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] + dind: false + agent_pool: mi300_1 + optional: true + working_dir: "/vllm-workspace/tests" + source_file_dependencies: + - vllm/v1/worker/gpu/ + - vllm/v1/worker/gpu_worker.py + - tests/v1/spec_decode/test_max_len.py + - tests/v1/spec_decode/test_rejection_sampler_utils.py + - tests/v1/spec_decode/test_synthetic_rejection_sampler_utils.py + - tests/v1/e2e/spec_decode/ + - vllm/platforms/rocm.py + commands: + - set -x + - export VLLM_USE_V2_MODEL_RUNNER=1 + - pytest -v -s v1/spec_decode/test_max_len.py -k "eagle or mtp" + - pytest -v -s v1/spec_decode/test_rejection_sampler_utils.py + - pytest -v -s v1/spec_decode/test_synthetic_rejection_sampler_utils.py + - pytest -v -s v1/e2e/spec_decode/eagle/ + - pytest -v -s v1/e2e/spec_decode/speculators/ + - pytest -v -s v1/e2e/spec_decode/mtp/ + #------------------------------------------------------ mi300 · models / basic -------------------------------------------------------# - label: ":amd: (MI300) Basic Models (Initialization)" # TBD @@ -2259,6 +2493,23 @@ steps: - VLLM_TEST_FORCE_LOAD_FORMAT=auto pytest -v -s quantization/ --ignore quantization/test_blackwell_moe.py --ignore quantization/test_rocm_moe.py --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT - if [ "$$BUILDKITE_PARALLEL_JOB" = "0" ]; then pytest -v -s rocm/test_moe_weight_replay.py; fi +- label: ":amd: (MI300) Quantized Fusions" # TBD + timeout_in_minutes: 45 + mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] + dind: false + agent_pool: mi300_1 + optional: true + working_dir: "/vllm-workspace/tests" + source_file_dependencies: + - tests/fusion + - vllm/model_executor/layers/fusion + - vllm/model_executor/kernels/linear + - vllm/model_executor/layers/quantization/compressed_tensors + - vllm/model_executor/layers/quantization/modelopt.py + - vllm/platforms/rocm.py + commands: + - pytest -v -s fusion/ + #--------------------------------------------------------- mi300 · samplers ----------------------------------------------------------# - label: ":amd: (MI300) Samplers" # TBD @@ -2412,8 +2663,8 @@ steps: source_file_dependencies: - vllm/v1/engine/ - tests/v1/engine/ - - vllm/platforms/rocm.py - tests/v1/test_tensor_ipc_queue.py + - vllm/platforms/rocm.py commands: - pytest -v -s v1/engine/test_preprocess_error_handling.py - pytest -v -s v1/engine --ignore v1/engine/test_preprocess_error_handling.py @@ -2626,6 +2877,23 @@ steps: - export BASELINE_FILE='/tmp/mooncake-ec-e2e/baseline.json' - bash tests/v1/ec_connector/integration/run_epd_mooncake_ec_full_pipeline.sh +- label: ":amd: (MI300) NixlConnector PD edge case" # TBD + timeout_in_minutes: 65 + mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] + dind: false + agent_pool: mi300_2 + num_gpus: 2 + optional: true + working_dir: "/vllm-workspace/tests" + source_file_dependencies: + - vllm/distributed/kv_transfer/kv_connector/v1/nixl/ + - vllm/v1/core/sched/ + - tests/v1/kv_connector/nixl_integration/ + - vllm/platforms/rocm.py + commands: + - uv pip install --system -r /vllm-workspace/requirements/kv_connectors_rocm.txt + - PREFILL_GPU_ID=0 DECODE_GPU_ID=1 ATTENTION_BACKEND=TRITON_ATTN bash v1/kv_connector/nixl_integration/run_edge_case_test.sh + - label: ":amd: (MI300) CrossLayer KV layout Distributed NixlConnector PD accuracy" # TBD timeout_in_minutes: 60 mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] @@ -2666,6 +2934,55 @@ steps: - pytest -v -s v1/engine/test_engine_core_client.py::test_kv_cache_events_dp - pytest -v -s distributed/test_utils.py +- label: ":amd: (MI300) Distributed NixlConnector PD accuracy" # TBD + timeout_in_minutes: 45 + mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] + dind: false + agent_pool: mi300_4 + num_gpus: 4 + optional: true + working_dir: "/vllm-workspace/tests" + source_file_dependencies: + - vllm/distributed/kv_transfer/kv_connector/v1/nixl/ + - tests/v1/kv_connector/nixl_integration/ + - vllm/platforms/rocm.py + commands: + - uv pip install --system -r /vllm-workspace/requirements/kv_connectors_rocm.txt + - ATTENTION_BACKEND=TRITON_ATTN bash v1/kv_connector/nixl_integration/config_sweep_accuracy_test.sh + +- label: ":amd: (MI300) Push NixlConnector PP prefill PD accuracy" # TBD + timeout_in_minutes: 55 + mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] + dind: false + agent_pool: mi300_4 + num_gpus: 4 + optional: true + working_dir: "/vllm-workspace/tests" + source_file_dependencies: + - vllm/distributed/kv_transfer/kv_connector/v1/nixl/ + - tests/v1/kv_connector/nixl_integration/ + - tests/v1/kv_connector/nixl_push_integration/ + - vllm/platforms/rocm.py + commands: + - uv pip install --system -r /vllm-workspace/requirements/kv_connectors_rocm.txt + - ATTENTION_BACKEND=TRITON_ATTN bash v1/kv_connector/nixl_push_integration/config_sweep_accuracy_test.sh + +- label: ":amd: (MI300) DP EP Distributed NixlConnector PD accuracy" # TBD + timeout_in_minutes: 30 + mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] + dind: false + agent_pool: mi300_4 + num_gpus: 4 + optional: true + working_dir: "/vllm-workspace/tests" + source_file_dependencies: + - vllm/distributed/kv_transfer/kv_connector/v1/nixl/ + - tests/v1/kv_connector/nixl_integration/ + - vllm/platforms/rocm.py + commands: + - uv pip install --system -r /vllm-workspace/requirements/kv_connectors_rocm.txt + - DP_EP=1 ATTENTION_BACKEND=TRITON_ATTN bash v1/kv_connector/nixl_integration/config_sweep_accuracy_test.sh + - label: ":amd: (MI300) Hybrid SSM NixlConnector PD accuracy" # TBD timeout_in_minutes: 80 mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] @@ -3648,7 +3965,11 @@ steps: - vllm/model_executor/models/qwen3.py - vllm/model_executor/models/qwen3_next.py - vllm/model_executor/models/qwen3_next_mtp.py + - vllm/distributed/ + - vllm/model_executor/layers/fused_moe/ - vllm/third_party/flash_linear_attention/ops/ + - tests/evals/gsm8k/ + - tests/utils.py - vllm/_aiter_ops.py - vllm/platforms/rocm.py commands: @@ -3780,14 +4101,44 @@ steps: commands: - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=evals/gsm8k/configs/models-turboquant-t3nc-rocm.txt -- label: ":amd: (MI355) LM Eval Small Models Distributed" - timeout_in_minutes: 55 +- label: ":amd: (MI355) LM Eval Spec Decode (Fixed-length FP8)" # TBD + timeout_in_minutes: 145 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] dind: false + agent_pool: mi355_4 + num_gpus: 4 + optional: true + working_dir: "/vllm-workspace/tests" + source_file_dependencies: + - tests/evals/gsm8k/ + - tests/utils.py + - vllm/distributed/ + - vllm/models/deepseek_v4/ + - vllm/model_executor/models/qwen3_dspark.py + - vllm/model_executor/layers/fused_moe/ + - vllm/v1/spec_decode/metrics.py + - vllm/v1/worker/gpu/spec_decode/dspark/ + - vllm/v1/worker/gpu/spec_decode/rejection_sampler.py + - vllm/v1/worker/gpu/spec_decode/speculator.py + - vllm/model_executor/layers/quantization/ + - vllm/v1/attention/ + - vllm/_aiter_ops.py + - vllm/platforms/rocm.py + commands: + - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-spec-decode-rocm.txt + +- label: ':amd: (MI355) LM Eval Small Models Distributed' + timeout_in_minutes: 145 + mirror_hardwares: + - amdexperimental + - amdproduction + - amdgfx950nightly + - amdmi355 + dind: false agent_pool: mi355_2 num_gpus: 2 optional: true - working_dir: "/vllm-workspace/tests" + working_dir: /vllm-workspace/tests source_file_dependencies: - csrc/ - vllm/model_executor/layers/quantization @@ -3795,11 +4146,22 @@ steps: - vllm/model_executor/model_loader/ - vllm/v1/attention/backends/ - vllm/v1/attention/selector.py + - vllm/v1/worker/ + - vllm/v1/core/ + - vllm/config/ + - tests/evals/gsm8k/configs/models-mi3xx-fp8-and-mixed.txt - vllm/_aiter_ops.py - vllm/platforms/rocm.py - - tests/evals/gsm8k/configs/models-mi3xx-fp8-and-mixed.txt + - tests/evals/gsm8k/ + - tests/utils.py + - vllm/distributed/ + - vllm/transformers_utils/configs/diffusion_gemma.py + - vllm/v1/attention/ops/ + - tests/evals/gsm8k/configs/models-small-tp-mi355.txt commands: - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-mi3xx-fp8-and-mixed.txt + - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-small-tp.txt + - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-small-tp-mi355.txt - label: ":amd: (MI355) MoE Refactor Integration Shard %N" timeout_in_minutes: 105 @@ -3820,6 +4182,7 @@ steps: - export VLLM_WORKER_MULTIPROC_METHOD=spawn - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=evals/gsm8k/configs/moe-refactor/config-rocm-shard-$$BUILDKITE_PARALLEL_JOB.txt + - label: ":amd: (MI355) Qwen3-30B-A3B-FP8-block Sync EPLB Accuracy" # TBD timeout_in_minutes: 25 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] @@ -4351,6 +4714,22 @@ steps: commands: - pytest -v -s models/test_initialization.py -k 'not test_can_initialize_small_subset' --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB +- label: ":amd: (MI355) Inkling" # TBD + timeout_in_minutes: 65 + mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] + dind: false + agent_pool: mi355_1 + optional: true + working_dir: "/vllm-workspace/tests" + source_file_dependencies: + - vllm/models/inkling/ + - vllm/cute_utils/ + - cmake/external_projects/tml_fa4.cmake + - tests/models/inkling/ + - vllm/platforms/rocm.py + commands: + - pytest -v -s models/inkling/rocm + #----------------------------------------------------- mi355 · models / language -----------------------------------------------------# - label: ":amd: (MI355 DPX) Language Models (Standard)" # TBD @@ -5105,7 +5484,8 @@ steps: - vllm/platforms/rocm.py optional: true commands: - - pytest -v -s v1/attention --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT + - pytest -v -s v1/attention --ignore=v1/attention/test_mla_backends.py --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT + - VLLM_ROCM_USE_AITER=1 pytest -v -s v1/attention/test_mla_backends.py --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT - label: ":amd: (MI355 DPX) V1 Core (MI355 suite)" timeout_in_minutes: 60 @@ -5501,6 +5881,34 @@ steps: - pip install 'modelscope<1.38' - pytest -v -s test_regression.py +- label: ':amd: (MI355) DeepSeek V4 MoE Integration' + timeout_in_minutes: 20 + source_file_dependencies: + - tests/models/test_deepseek_v4_vl_rocm.py + - vllm/models/deepseek_v4/amd/ + - vllm/models/deepseek_v4/common/ + - vllm/model_executor/layers/fused_moe/ + - vllm/model_executor/layers/activation.py + - vllm/model_executor/layers/linear.py + - vllm/config/ + - vllm/forward_context.py + - vllm/v1/worker/workspace.py + - vllm/_aiter_ops.py + - vllm/platforms/rocm.py + - vllm/envs.py + commands: + - VLLM_ROCM_USE_AITER_MOE=0 pytest -v -s models/test_deepseek_v4_vl_rocm.py + dind: false + working_dir: /vllm-workspace/tests + agent_pool: mi355_1 + num_gpus: 1 + mirror_hardwares: + - amdexperimental + - amdproduction + - amdgfx950nightly + - amdmi355 + optional: true + - label: ':amd: (MI355) Quantized MoE' timeout_in_minutes: 45 working_dir: /vllm-workspace/ diff --git a/.buildkite/test_areas/attention.yaml b/.buildkite/test_areas/attention.yaml index e11108d925..b9f430a20e 100644 --- a/.buildkite/test_areas/attention.yaml +++ b/.buildkite/test_areas/attention.yaml @@ -43,3 +43,22 @@ steps: commands: - pytest -v -s v1/attention --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT parallelism: 2 + mirror: + amd: + label: ":amd: (MI355 DPX) V1 Attention Shard %N" + dind: false + device: mi355_dpx + timeout_in_minutes: 125 + depends_on: + - image-build-amd + source_file_dependencies: + - vllm/config/attention.py + - vllm/model_executor/layers/attention + - vllm/v1/attention + - tests/v1/attention + - vllm/_aiter_ops.py + - vllm/envs.py + - vllm/platforms/rocm.py + commands: + - pytest -v -s v1/attention --ignore=v1/attention/test_mla_backends.py --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT + - VLLM_ROCM_USE_AITER=1 pytest -v -s v1/attention/test_mla_backends.py --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT diff --git a/.buildkite/test_areas/disaggregated.yaml b/.buildkite/test_areas/disaggregated.yaml index 43abe2ce01..b9bd59583b 100644 --- a/.buildkite/test_areas/disaggregated.yaml +++ b/.buildkite/test_areas/disaggregated.yaml @@ -79,6 +79,22 @@ steps: commands: - bash /vllm-workspace/.buildkite/scripts/install-kv-connectors.sh - bash v1/kv_connector/nixl_push_integration/config_sweep_accuracy_test.sh + mirror: + amd: + label: ":amd: (MI300) Push NixlConnector PP prefill PD accuracy" + dind: false + device: mi300_4 + timeout_in_minutes: 55 + depends_on: + - image-build-amd + source_file_dependencies: + - vllm/distributed/kv_transfer/kv_connector/v1/nixl/ + - tests/v1/kv_connector/nixl_integration/ + - tests/v1/kv_connector/nixl_push_integration/ + - vllm/platforms/rocm.py + commands: + - uv pip install --system -r /vllm-workspace/requirements/kv_connectors_rocm.txt + - ATTENTION_BACKEND=TRITON_ATTN bash v1/kv_connector/nixl_push_integration/config_sweep_accuracy_test.sh - label: ":nvidia: (L4) DP EP Distributed NixlConnector PD accuracy" key: dp-ep-distributed-nixlconnector-pd-accuracy-tests-4-gpus @@ -180,6 +196,22 @@ steps: commands: - bash /vllm-workspace/.buildkite/scripts/install-kv-connectors.sh - bash v1/kv_connector/nixl_integration/run_edge_case_test.sh + mirror: + amd: + label: ":amd: (MI300) NixlConnector PD edge case" + dind: false + device: mi300_2 + timeout_in_minutes: 65 + depends_on: + - image-build-amd + source_file_dependencies: + - vllm/distributed/kv_transfer/kv_connector/v1/nixl/ + - vllm/v1/core/sched/ + - tests/v1/kv_connector/nixl_integration/ + - vllm/platforms/rocm.py + commands: + - uv pip install --system -r /vllm-workspace/requirements/kv_connectors_rocm.txt + - PREFILL_GPU_ID=0 DECODE_GPU_ID=1 ATTENTION_BACKEND=TRITON_ATTN bash v1/kv_connector/nixl_integration/run_edge_case_test.sh - label: ":nvidia: (L4) Hybrid SSM NixlConnector PD prefix cache" key: hybrid-ssm-nixlconnector-pd-prefix-cache-2-gpus diff --git a/.buildkite/test_areas/kernels.yaml b/.buildkite/test_areas/kernels.yaml index c53c91cb63..46a969416b 100644 --- a/.buildkite/test_areas/kernels.yaml +++ b/.buildkite/test_areas/kernels.yaml @@ -47,7 +47,7 @@ steps: label: ":amd: (MI300) Core Operation Kernels Shard %N" dind: false device: mi300_1 - timeout_in_minutes: 40 + timeout_in_minutes: 45 working_dir: "/vllm-workspace/tests" depends_on: - image-build-amd @@ -143,6 +143,33 @@ steps: commands: - pytest -v -s kernels/test_fused_deepseek_v4_*.py - pytest -v -s models/test_deepseek_v4_mega_moe.py + mirror: + amd: + label: ":amd: (MI355) DeepSeek V4 MoE Integration" + dind: false + device: mi355_1 + num_devices: 1 + timeout_in_minutes: 20 + working_dir: /vllm-workspace/tests + depends_on: + - image-build-amd + source_file_dependencies: + - tests/models/test_deepseek_v4_vl_rocm.py + - vllm/models/deepseek_v4/amd/ + - vllm/models/deepseek_v4/common/ + - vllm/model_executor/layers/fused_moe/ + - vllm/model_executor/layers/activation.py + - vllm/model_executor/layers/linear.py + - vllm/config/ + - vllm/forward_context.py + - vllm/v1/worker/workspace.py + - vllm/_aiter_ops.py + - vllm/platforms/rocm.py + - vllm/envs.py + commands: + # Common qnorm/RoPE/cache kernels already run in the H100 AMD mirror. + # Pin the tested BF16 Triton routing and shared-expert path before imports. + - VLLM_ROCM_USE_AITER_MOE=0 pytest -v -s models/test_deepseek_v4_vl_rocm.py # Own job so mHC never shares a process with FlashInfer's import-time # ptxas override. diff --git a/.buildkite/test_areas/lm_eval.yaml b/.buildkite/test_areas/lm_eval.yaml index 9f99e1c53f..971e308d25 100644 --- a/.buildkite/test_areas/lm_eval.yaml +++ b/.buildkite/test_areas/lm_eval.yaml @@ -186,7 +186,7 @@ steps: label: ":amd: (MI355) LM Eval Small Models Distributed" dind: false device: mi355_2 - timeout_in_minutes: 55 + timeout_in_minutes: 145 depends_on: - image-build-amd source_file_dependencies: @@ -196,11 +196,22 @@ steps: - vllm/model_executor/model_loader/ - vllm/v1/attention/backends/ - vllm/v1/attention/selector.py + - vllm/v1/worker/ + - vllm/v1/core/ + - vllm/config/ - tests/evals/gsm8k/configs/models-mi3xx-fp8-and-mixed.txt - vllm/_aiter_ops.py - vllm/platforms/rocm.py + - tests/evals/gsm8k/ + - tests/utils.py + - vllm/distributed/ + - vllm/transformers_utils/configs/diffusion_gemma.py + - vllm/v1/attention/ops/ commands: - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-mi3xx-fp8-and-mixed.txt + - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-small-tp.txt + # Dense MLA PCP-only accuracy; DP1/DCP1. + - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-small-tp-mi355.txt - label: ":nvidia: (B200) LM Eval HiSparse Nightly" key: lm-eval-hisparse-nightly-4xb200 @@ -319,10 +330,10 @@ steps: - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-spec-decode.txt mirror: amd: - label: ":amd: (MI355) LM Eval Spec Decode" + label: ":amd: (MI355) LM Eval Spec Decode (Fixed-length FP8)" dind: false device: mi355_4 - timeout_in_minutes: 120 + timeout_in_minutes: 145 depends_on: - image-build-amd source_file_dependencies: @@ -355,6 +366,9 @@ steps: - vllm/v1/worker/ - vllm/_aiter_ops.py - vllm/platforms/rocm.py + - tests/evals/gsm8k/ + - tests/utils.py + - vllm/distributed/ commands: - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-spec-decode-rocm.txt @@ -951,6 +965,22 @@ steps: - tests/evals/gsm8k/test_gsm8k_offloading.py commands: - pytest -s -v evals/gsm8k/test_gsm8k_offloading.py -k "nemotron-h-8b or gemma-4-e4b-it" + mirror: + amd: + label: ":amd: (MI300) LM Eval KV-Offload" + dind: false + device: mi300_1 + timeout_in_minutes: 55 + depends_on: + - image-build-amd + working_dir: /vllm-workspace/tests + source_file_dependencies: + - vllm/distributed/kv_transfer/kv_connector/v1/offloading/ + - vllm/distributed/kv_transfer/kv_connector/v1/simple_cpu_offload_connector.py + - vllm/v1/kv_offload/ + - vllm/v1/simple_kv_offload/ + - tests/evals/gsm8k/test_gsm8k_offloading.py + - vllm/platforms/rocm.py - label: ":nvidia: (H100) LM Eval KV-Offload Medium" key: kv-offload-medium @@ -965,6 +995,22 @@ steps: - tests/evals/gsm8k/test_gsm8k_offloading.py commands: - pytest -s -v evals/gsm8k/test_gsm8k_offloading.py -k "qwen3.5-35b or deepseek-v2-lite" + mirror: + amd: + label: ":amd: (MI300) LM Eval KV-Offload Medium" + dind: false + device: mi300_2 + timeout_in_minutes: 70 + depends_on: + - image-build-amd + working_dir: /vllm-workspace/tests + source_file_dependencies: + - vllm/distributed/kv_transfer/kv_connector/v1/offloading/ + - vllm/distributed/kv_transfer/kv_connector/v1/simple_cpu_offload_connector.py + - vllm/v1/kv_offload/ + - vllm/v1/simple_kv_offload/ + - tests/evals/gsm8k/test_gsm8k_offloading.py + - vllm/platforms/rocm.py - label: ":nvidia: (H100) LM Eval KV-Offload Large" key: kv-offload-large @@ -979,6 +1025,24 @@ steps: - tests/evals/gsm8k/test_gsm8k_offloading.py commands: - pytest -s -v evals/gsm8k/test_gsm8k_offloading.py -k "deepseek-v4-flash" + mirror: + amd: + label: ":amd: (MI300) LM Eval KV-Offload Large" + dind: false + device: mi300_4 + timeout_in_minutes: 65 + depends_on: + - image-build-amd + working_dir: /vllm-workspace/tests + source_file_dependencies: + - vllm/distributed/kv_transfer/kv_connector/v1/offloading/ + - vllm/distributed/kv_transfer/kv_connector/v1/simple_cpu_offload_connector.py + - vllm/v1/kv_offload/ + - vllm/v1/simple_kv_offload/ + - tests/evals/gsm8k/test_gsm8k_offloading.py + - vllm/platforms/rocm.py + commands: + - VLLM_ROCM_USE_AITER=1 pytest -s -v evals/gsm8k/test_gsm8k_offloading.py -k "deepseek-v4-flash" - label: ":nvidia: (H200 MIG 35GB) MRCR Eval Small Models" key: mrcr-eval-small-models diff --git a/.buildkite/test_areas/models_basic.yaml b/.buildkite/test_areas/models_basic.yaml index 83a08cfc24..62805e90f6 100644 --- a/.buildkite/test_areas/models_basic.yaml +++ b/.buildkite/test_areas/models_basic.yaml @@ -95,6 +95,23 @@ steps: commands: # FA4 kernel tests require SM100; the suite skips them elsewhere. - pytest -v -s models/inkling + mirror: + amd: + label: ":amd: (MI355) Inkling" + dind: false + device: mi355_1 + timeout_in_minutes: 65 + working_dir: "/vllm-workspace/tests" + depends_on: + - image-build-amd + source_file_dependencies: + - vllm/models/inkling/ + - vllm/cute_utils/ + - cmake/external_projects/tml_fa4.cmake + - tests/models/inkling/ + - vllm/platforms/rocm.py + commands: + - pytest -v -s models/inkling/rocm - label: ":nvidia: (B200) Kimi K3" key: kimi-k3-unit-tests-b200 diff --git a/.buildkite/test_areas/quantization.yaml b/.buildkite/test_areas/quantization.yaml index d1f47cf2a7..122679553f 100644 --- a/.buildkite/test_areas/quantization.yaml +++ b/.buildkite/test_areas/quantization.yaml @@ -58,6 +58,22 @@ steps: - vllm/model_executor/layers/quantization/modelopt.py commands: - pytest -v -s fusion/ + mirror: + amd: + label: ":amd: (MI300) Quantized Fusions" + dind: false + device: mi300_1 + timeout_in_minutes: 45 + working_dir: "/vllm-workspace/tests" + depends_on: + - image-build-amd + source_file_dependencies: + - tests/fusion + - vllm/model_executor/layers/fusion + - vllm/model_executor/kernels/linear + - vllm/model_executor/layers/quantization/compressed_tensors + - vllm/model_executor/layers/quantization/modelopt.py + - vllm/platforms/rocm.py - label: ":nvidia: (B200) Quantized MoE" key: quantized-moe-test-b200 diff --git a/.buildkite/test_areas/torch_abi.yaml b/.buildkite/test_areas/torch_abi.yaml index 201f9b6093..ee95203a01 100644 --- a/.buildkite/test_areas/torch_abi.yaml +++ b/.buildkite/test_areas/torch_abi.yaml @@ -12,3 +12,22 @@ steps: - setup.py commands: - python3 /vllm-workspace/.buildkite/check-torch-abi.py + mirror: + amd: + label: ":amd: (MI250) Torch Stable ABI Audit" + dind: false + device: mi300_1 + timeout_in_minutes: 35 + depends_on: + - image-build-amd + no_gpu: true + working_dir: /vllm-workspace/ + source_file_dependencies: + - .buildkite/check-torch-abi.py + - csrc/ + - cmake/ + - setup.py + - vllm/platforms/rocm.py + commands: + - uv pip install --system torch-abi-audit==0.0.1 + - python3 /vllm-workspace/.buildkite/check-torch-abi.py diff --git a/tests/evals/gsm8k/configs/DeepSeek-V2-Lite-Instruct-FP8-TP1-PCP2-ROCm.yaml b/tests/evals/gsm8k/configs/DeepSeek-V2-Lite-Instruct-FP8-TP1-PCP2-ROCm.yaml new file mode 100644 index 0000000000..0275c9941a --- /dev/null +++ b/tests/evals/gsm8k/configs/DeepSeek-V2-Lite-Instruct-FP8-TP1-PCP2-ROCm.yaml @@ -0,0 +1,24 @@ +model_name: "RedHatAI/DeepSeek-Coder-V2-Lite-Instruct-FP8" +accuracy_threshold: 0.72 +num_questions: 1319 +num_fewshot: 5 +rocm_request_timeout_seconds: 1800 +# Dense MLA PCP on MI355; DP1/DCP1, eager execution, and Triton MoE. +server_args: >- + --revision efe1ced428db63e7ccbcf367334596f77e9af140 + --code-revision e434a23f91ba5b4923cf6c9d9a238eb4a08e3a11 + --dtype bfloat16 + --enforce-eager + --max-model-len 4096 + --max-num-seqs 8 + --max-num-batched-tokens 4096 + --tensor-parallel-size 1 + --prefill-context-parallel-size 2 + --enable-expert-parallel + --moe-backend triton + --attention-config '{"backend":"ROCM_AITER_MLA","mla_prefill_backend":"ROCM_AITER_FA"}' + --kv-cache-dtype auto +env: + VLLM_USE_V2_MODEL_RUNNER: "1" + VLLM_ROCM_USE_AITER: "1" + VLLM_WORKER_MULTIPROC_METHOD: "spawn" diff --git a/tests/evals/gsm8k/configs/models-qwen35-mi355.txt b/tests/evals/gsm8k/configs/models-qwen35-mi355.txt index 49925c827e..13ff05f870 100644 --- a/tests/evals/gsm8k/configs/models-qwen35-mi355.txt +++ b/tests/evals/gsm8k/configs/models-qwen35-mi355.txt @@ -1,3 +1,4 @@ Qwen3.5-35B-A3B-DEP2.yaml +Qwen3.5-35B-A3B-FP8-DEP2.yaml Qwen3.5-35B-A3B-MXFP4-AITER-TP2.yaml Qwen3.5-35B-A3B-MXFP4-EMU-TP2.yaml diff --git a/tests/evals/gsm8k/configs/models-small-tp-mi355.txt b/tests/evals/gsm8k/configs/models-small-tp-mi355.txt new file mode 100644 index 0000000000..78283f92af --- /dev/null +++ b/tests/evals/gsm8k/configs/models-small-tp-mi355.txt @@ -0,0 +1,2 @@ +# Dense MLA PCP accuracy on MI355. +DeepSeek-V2-Lite-Instruct-FP8-TP1-PCP2-ROCm.yaml