diff --git a/.buildkite/test-amd.yaml b/.buildkite/test-amd.yaml index 22856d837f..0dc52c87ba 100644 --- a/.buildkite/test-amd.yaml +++ b/.buildkite/test-amd.yaml @@ -2014,6 +2014,19 @@ steps: commands: - pytest -v -s models/multimodal/generation/test_common.py -m 'split(group=1) and not core_model' +- label: ":amd: (MI300) Multimodal Models (PPL)" + 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/ + - tests/models/multimodal/generation_ppl_test/ + commands: + - pytest -v -s models/multimodal/generation_ppl_test/ + - label: ":amd: (MI300) Multimodal Models (Standard) 3: llava + qwen2_vl" # TBD timeout_in_minutes: 55 mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] @@ -2542,6 +2555,87 @@ steps: - pytest -v -s v1/e2e/spec_decode/speculators/ - pytest -v -s v1/e2e/spec_decode/mtp/ +- label: ":amd: (MI300) Spec Decode DeepSeek MTP Parallel Load" + 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/spec_decode/llm_base_proposer.py + - vllm/v1/spec_decode/eagle.py + - vllm/v1/worker/gpu/spec_decode/eagle/ + - vllm/model_executor/models/deepseek_mtp.py + - vllm/model_executor/models/deepseek_v2.py + - tests/v1/e2e/spec_decode/test_mtp_parallel_load.py + - vllm/distributed/ + - vllm/model_executor/model_loader/ + - vllm/model_executor/layers/ + - vllm/v1/attention/ + - vllm/v1/engine/ + - vllm/v1/spec_decode/ + - vllm/v1/worker/gpu/spec_decode/ + - vllm/v1/worker/gpu_model_runner.py + - vllm/platforms/rocm.py + commands: + - pytest -v -s v1/e2e/spec_decode/test_mtp_parallel_load.py + +- label: ":amd: (MI300) Spec Decode AL DFlash Nightly" + timeout_in_minutes: 120 + 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/models/qwen3_dflash.py + - vllm/model_executor/models/qwen3_dflash2.py + - vllm/model_executor/models/qwen3_5.py + - vllm/model_executor/models/laguna_dflash.py + - tests/v1/e2e/spec_decode/ + - vllm/v1/attention/ + - vllm/v1/sample/ + - vllm/model_executor/model_loader/ + - vllm/model_executor/layers/ + - vllm/model_executor/models/qwen2.py + - vllm/model_executor/models/qwen3.py + - vllm/model_executor/models/laguna.py + - vllm/platforms/rocm.py + commands: + - pytest -v -s v1/e2e/spec_decode/acceptance_rates/dflash/ -k "not dflash2" + +- label: ":amd: (MI300) Spec Decode AL DSpark Nightly" + 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/spec_decode/ + - vllm/v1/worker/gpu/spec_decode/ + - vllm/model_executor/models/qwen3_dspark.py + - vllm/model_executor/models/gemma4_dspark.py + - tests/v1/e2e/spec_decode/ + - vllm/v1/attention/ + - vllm/v1/sample/ + - vllm/model_executor/model_loader/ + - vllm/model_executor/layers/ + - vllm/model_executor/models/qwen2.py + - vllm/model_executor/models/qwen3.py + - vllm/model_executor/models/qwen3_dflash.py + - vllm/model_executor/models/gemma4.py + - vllm/model_executor/models/gemma4_mm.py + - vllm/model_executor/models/gemma4_unified.py + - vllm/model_executor/models/gemma4_mtp.py + - vllm/platforms/rocm.py + commands: + - pytest -v -s v1/e2e/spec_decode/acceptance_rates/dspark/ + - label: ":amd: (MI300) V1 Spec Decode" # TBD timeout_in_minutes: 50 mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] @@ -4902,6 +4996,32 @@ 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 DPX) FP4 and INT4 MoE Kernels" + 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: + - 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) DeepEP FP8 MoE Kernels" # TBD timeout_in_minutes: 55 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355] @@ -4960,6 +5080,23 @@ steps: - 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) Qwen4 Exp" + 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/models/qwen4_exp/ + - vllm/config/compilation.py + - vllm/v1/attention/backends/short_conv_attn.py + - tests/models/qwen4_exp/ + commands: + - pytest -v -s models/qwen4_exp/test_qsa_amd.py models/qwen4_exp/test_qsa_prepare_amd.py + # PLE and QSA import conflicting HC registrations in a shared process. + - pytest -v -s models/qwen4_exp/test_ple.py + - label: ":amd: (MI355 DPX) GLM5Next" timeout_in_minutes: 35 mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355]