diff --git a/.buildkite/test-amd.yaml b/.buildkite/test-amd.yaml index ca790a7e7d..ef30158430 100644 --- a/.buildkite/test-amd.yaml +++ b/.buildkite/test-amd.yaml @@ -2209,75 +2209,75 @@ steps: #-------------------------------------------------- mi300 · models / transformers ---------------------------------------------------# -- label: ":amd: (MI300) Transformers Nightly Models (Initialization) Shard %N" # TBD - timeout_in_minutes: 65 - mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] - dind: false - agent_pool: mi300_1 - parallelism: 6 - optional: true - working_dir: "/vllm-workspace/" - source_file_dependencies: - - vllm/model_executor/models/ - - vllm/model_executor/model_loader/ - - vllm/multimodal/ - - vllm/model_executor/layers/ - - vllm/v1/attention/backends/ - - vllm/v1/attention/selector.py - - vllm/_aiter_ops.py - - vllm/platforms/rocm.py - - tests/models/ - commands: - - pip install --upgrade git+https://github.com/huggingface/transformers - - pytest -v -s tests/models/test_initialization.py --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB +# - label: ":amd: (MI300) Transformers Nightly Models (Initialization) Shard %N" # TBD +# timeout_in_minutes: 65 +# mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] +# dind: false +# agent_pool: mi300_1 +# parallelism: 6 +# optional: true +# working_dir: "/vllm-workspace/" +# source_file_dependencies: +# - vllm/model_executor/models/ +# - vllm/model_executor/model_loader/ +# - vllm/multimodal/ +# - vllm/model_executor/layers/ +# - vllm/v1/attention/backends/ +# - vllm/v1/attention/selector.py +# - vllm/_aiter_ops.py +# - vllm/platforms/rocm.py +# - tests/models/ +# commands: +# - pip install --upgrade git+https://github.com/huggingface/transformers +# - pytest -v -s tests/models/test_initialization.py --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB -- label: ":amd: (MI300) Transformers Nightly Models (Processing) Shard %N" # TBD - timeout_in_minutes: 145 - mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] - dind: false - agent_pool: mi300_1 - parallelism: 8 - optional: true - working_dir: "/vllm-workspace/" - source_file_dependencies: - - vllm/model_executor/models/ - - vllm/model_executor/model_loader/ - - vllm/multimodal/ - - vllm/model_executor/layers/ - - vllm/v1/attention/backends/ - - vllm/v1/attention/selector.py - - vllm/_aiter_ops.py - - vllm/platforms/rocm.py - - tests/models/ - commands: - - pip install --upgrade git+https://github.com/huggingface/transformers - - pytest -v -s tests/models/multimodal/processing/ --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB +# - label: ":amd: (MI300) Transformers Nightly Models (Processing) Shard %N" # TBD +# timeout_in_minutes: 145 +# mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] +# dind: false +# agent_pool: mi300_1 +# parallelism: 8 +# optional: true +# working_dir: "/vllm-workspace/" +# source_file_dependencies: +# - vllm/model_executor/models/ +# - vllm/model_executor/model_loader/ +# - vllm/multimodal/ +# - vllm/model_executor/layers/ +# - vllm/v1/attention/backends/ +# - vllm/v1/attention/selector.py +# - vllm/_aiter_ops.py +# - vllm/platforms/rocm.py +# - tests/models/ +# commands: +# - pip install --upgrade git+https://github.com/huggingface/transformers +# - pytest -v -s tests/models/multimodal/processing/ --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB -- label: ":amd: (MI300) Transformers Nightly Models (Single)" # TBD - timeout_in_minutes: 50 - mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] - dind: false - agent_pool: mi300_1 - optional: true - working_dir: "/vllm-workspace/" - source_file_dependencies: - - vllm/model_executor/models/ - - vllm/model_executor/model_loader/ - - vllm/multimodal/ - - vllm/model_executor/layers/ - - vllm/v1/attention/backends/ - - vllm/v1/attention/selector.py - - vllm/_aiter_ops.py - - vllm/platforms/rocm.py - - tests/models/ - - examples/ - commands: - - pip install --upgrade git+https://github.com/huggingface/transformers - - pytest -v -s tests/models/transformers/test_backend.py - - pytest -v -s tests/models/multimodal/test_mapping.py - - python3 examples/basic/offline_inference/chat.py - - python3 examples/generate/multimodal/vision_language_offline.py --model-type qwen2_5_vl - - VLLM_WORKER_MULTIPROC_METHOD=spawn python3 examples/generate/multimodal/audio_language_offline.py --model-type whisper +# - label: ":amd: (MI300) Transformers Nightly Models (Single)" # TBD +# timeout_in_minutes: 50 +# mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] +# dind: false +# agent_pool: mi300_1 +# optional: true +# working_dir: "/vllm-workspace/" +# source_file_dependencies: +# - vllm/model_executor/models/ +# - vllm/model_executor/model_loader/ +# - vllm/multimodal/ +# - vllm/model_executor/layers/ +# - vllm/v1/attention/backends/ +# - vllm/v1/attention/selector.py +# - vllm/_aiter_ops.py +# - vllm/platforms/rocm.py +# - tests/models/ +# - examples/ +# commands: +# - pip install --upgrade git+https://github.com/huggingface/transformers +# - pytest -v -s tests/models/transformers/test_backend.py +# - pytest -v -s tests/models/multimodal/test_mapping.py +# - python3 examples/basic/offline_inference/chat.py +# - python3 examples/generate/multimodal/vision_language_offline.py --model-type qwen2_5_vl +# - VLLM_WORKER_MULTIPROC_METHOD=spawn python3 examples/generate/multimodal/audio_language_offline.py --model-type whisper #---------------------------------------------------------- mi300 · plugins ----------------------------------------------------------#