diff --git a/.buildkite/test-amd.yaml b/.buildkite/test-amd.yaml index 76207e5b36..b47ccd3f5a 100644 --- a/.buildkite/test-amd.yaml +++ b/.buildkite/test-amd.yaml @@ -798,32 +798,6 @@ steps: commands: - pytest -v -s v1/attention -- label: V1 Core + KV + Metrics # TBD - timeout_in_minutes: 60 - mirror_hardwares: [amdexperimental, amdproduction, amdgfx90anightly, amdmi250] - agent_pool: mi250_1 - optional: true - working_dir: "/vllm-workspace/tests" - source_file_dependencies: - - vllm/ - - tests/v1/core - - tests/v1/executor - - tests/v1/kv_offload - - tests/v1/worker - - tests/v1/kv_connector/unit - - tests/v1/metrics - - tests/entrypoints/openai/correctness/test_lmeval.py - commands: - - uv pip install --system -r /vllm-workspace/requirements/kv_connectors_rocm.txt - - pytest -v -s -m 'not cpu_test' v1/core - - pytest -v -s v1/executor - - pytest -v -s v1/kv_offload - - pytest -v -s v1/worker - - pytest -v -s -m 'not cpu_test' v1/kv_connector/unit - - pytest -v -s -m 'not cpu_test' v1/metrics - - pip install -U git+https://github.com/robertgshaw2-redhat/lm-evaluation-harness.git@streaming-api - - pytest -v -s entrypoints/openai/correctness/test_lmeval.py::test_lm_eval_accuracy_v1_engine - - label: V1 Sample + Logits # TBD timeout_in_minutes: 60 mirror_hardwares: [amdexperimental, amdproduction, amdgfx90anightly, amdmi250] @@ -1279,6 +1253,7 @@ steps: timeout_in_minutes: 180 mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] agent_pool: mi300_1 + optional: true fast_check: true torch_nightly: true working_dir: "/vllm-workspace/tests" @@ -1299,6 +1274,7 @@ steps: agent_pool: mi300_1 fast_check: true torch_nightly: true + optional: true working_dir: "/vllm-workspace/tests" source_file_dependencies: - vllm/ @@ -1312,6 +1288,7 @@ steps: timeout_in_minutes: 180 mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] agent_pool: mi300_1 + optional: true fast_check: true torch_nightly: true working_dir: "/vllm-workspace/tests" @@ -1328,6 +1305,7 @@ steps: timeout_in_minutes: 180 mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] agent_pool: mi300_1 + optional: true fast_check: true torch_nightly: true working_dir: "/vllm-workspace/tests" @@ -1728,6 +1706,7 @@ steps: timeout_in_minutes: 180 mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] agent_pool: mi300_1 + optional: true parallelism: 2 working_dir: "/vllm-workspace/tests" source_file_dependencies: @@ -1786,6 +1765,7 @@ steps: timeout_in_minutes: 180 mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300] agent_pool: mi300_1 + optional: true working_dir: "/vllm-workspace/tests" source_file_dependencies: - vllm/ diff --git a/.buildkite/test_areas/engine.yaml b/.buildkite/test_areas/engine.yaml index c8b2d66a41..34d3aedd4c 100644 --- a/.buildkite/test_areas/engine.yaml +++ b/.buildkite/test_areas/engine.yaml @@ -36,6 +36,12 @@ steps: commands: - pytest -v -s v1/engine/test_preprocess_error_handling.py - pytest -v -s v1/engine --ignore v1/engine/test_preprocess_error_handling.py + mirror: + amd: + device: mi300_1 + timeout_in_minutes: 40 + depends_on: + - image-build-amd - label: e2e Scheduling (1 GPU) key: e2e-scheduling-1-gpu @@ -46,6 +52,12 @@ steps: - tests/v1/e2e/general/ commands: - pytest -v -s v1/e2e/general/test_async_scheduling.py + mirror: + amd: + device: mi250_1 + timeout_in_minutes: 60 + depends_on: + - image-build-amd - label: e2e Core (1 GPU) key: e2e-core-1-gpu diff --git a/.buildkite/test_areas/entrypoints.yaml b/.buildkite/test_areas/entrypoints.yaml index f9ddf26030..878ea3694a 100644 --- a/.buildkite/test_areas/entrypoints.yaml +++ b/.buildkite/test_areas/entrypoints.yaml @@ -43,6 +43,12 @@ steps: commands: - export VLLM_WORKER_MULTIPROC_METHOD=spawn - pytest -v -s entrypoints/openai/chat_completion --ignore=entrypoints/openai/chat_completion/test_chat_with_tool_reasoning.py --ignore=entrypoints/openai/chat_completion/test_oot_registration.py + mirror: + amd: + device: mi300_1 + timeout_in_minutes: 80 + depends_on: + - image-build-amd - label: Entrypoints Integration (API Server openai - Part 2) key: entrypoints-integration-api-server-openai-part-2 @@ -55,6 +61,12 @@ steps: commands: - pytest -v -s entrypoints/openai/completion --ignore=entrypoints/openai/completion/test_tensorizer_entrypoint.py - pytest -v -s entrypoints/test_chat_utils.py + mirror: + amd: + device: mi300_1 + timeout_in_minutes: 60 + depends_on: + - image-build-amd - label: Entrypoints Integration (API Server openai - Part 3) key: entrypoints-integration-api-server-openai-part-3 @@ -67,7 +79,13 @@ steps: - tests/entrypoints/test_chat_utils commands: - export VLLM_WORKER_MULTIPROC_METHOD=spawn - - pytest -v -s entrypoints/openai --ignore=entrypoints/openai/chat_completion --ignore=entrypoints/openai/completion --ignore=entrypoints/openai/correctness/ --ignore=entrypoints/openai/tool_parsers/ --ignore=entrypoints/openai/responses --ignore=entrypoints/openai/test_multi_api_servers.py + - pytest -v -s entrypoints/openai --ignore=entrypoints/openai/chat_completion --ignore=entrypoints/openai/completion --ignore=entrypoints/openai/correctness/ --ignore=entrypoints/openai/tool_parsers/ --ignore=entrypoints/openai/responses --ignore=entrypoints/openai/test_multi_api_servers.py + mirror: + amd: + device: mi300_1 + timeout_in_minutes: 60 + depends_on: + - image-build-amd - label: Entrypoints Integration (API Server 2) key: entrypoints-integration-api-server-2 @@ -83,6 +101,11 @@ steps: - pytest -v -s entrypoints/serve/instrumentator - PYTHONPATH=/vllm-workspace pytest -v -s entrypoints/rpc - pytest -v -s tool_use + mirror: + amd: + device: mi300_1 + depends_on: + - image-build-amd - label: Entrypoints Integration (Speech to Text) key: entrypoints-integration-speech_to_text diff --git a/.buildkite/test_areas/kernels.yaml b/.buildkite/test_areas/kernels.yaml index fee7728938..3f296ceb85 100644 --- a/.buildkite/test_areas/kernels.yaml +++ b/.buildkite/test_areas/kernels.yaml @@ -62,6 +62,19 @@ steps: commands: - pytest -v -s kernels/quantization --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT parallelism: 2 + mirror: + amd: + device: mi300_1 + source_file_dependencies: + - csrc/quantization/ + - vllm/model_executor/layers/quantization + - tests/kernels/quantization + - tests/kernels/quantization/test_rocm_skinny_gemms.py + - vllm/_aiter_ops.py + - vllm/platforms/rocm.py + - vllm/model_executor/kernels/ + depends_on: + - image-build-amd - label: Kernels MoE Test %N key: kernels-moe-test diff --git a/.buildkite/test_areas/models_language.yaml b/.buildkite/test_areas/models_language.yaml index e42675c029..cca1509294 100644 --- a/.buildkite/test_areas/models_language.yaml +++ b/.buildkite/test_areas/models_language.yaml @@ -92,6 +92,12 @@ steps: - tests/models/language/pooling commands: - pytest -v -s models/language/pooling -m 'not core_model' + mirror: + amd: + device: mi300_1 + timeout_in_minutes: 100 + depends_on: + - image-build-amd - label: Language Models Test (MTEB) key: language-models-test-mteb