91ed2859c7
Signed-off-by: Ganesh R <ganesh.r@amd.com> Co-authored-by: Kevin H. Luu <khluu000@gmail.com> Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
289 lines
11 KiB
YAML
289 lines
11 KiB
YAML
group: CPU
|
|
depends_on: []
|
|
steps:
|
|
- label: CPU-Kernel Tests Shard %N
|
|
key: cpu-kernel-tests
|
|
depends_on: []
|
|
device: intel_cpu
|
|
no_plugin: true
|
|
source_file_dependencies:
|
|
- csrc/cpu/
|
|
- cmake/cpu_extension.cmake
|
|
- CMakeLists.txt
|
|
- vllm/_custom_ops.py
|
|
- tests/kernels/attention/test_cpu_attn.py
|
|
- tests/v1/attention/test_group_head_counts.py
|
|
- tests/kernels/attention/test_amx_mla.py
|
|
- vllm/v1/attention/backends/mla/amx_mla.py
|
|
- vllm/model_executor/layers/attention/mla_attention.py
|
|
- tests/kernels/test_deepseek_v4_cpu_kernels.py
|
|
- tests/kernels/moe/test_cpu_fused_moe.py
|
|
- tests/kernels/moe/test_cpu_quant_fused_moe.py
|
|
- tests/kernels/moe/test_zen_cpu_int8_moe.py
|
|
- tests/test_zentorch_version_pin.py
|
|
- vllm/model_executor/layers/fused_moe/experts/cpu_moe.py
|
|
- tests/kernels/test_onednn.py
|
|
- tests/kernels/test_cpu_fused_sampling.py
|
|
- tests/kernels/test_awq_int4_to_int8.py
|
|
- tests/kernels/quantization/test_cpu_fp8_scaled_mm.py
|
|
- tests/kernels/quantization/test_zen_da8w4.py
|
|
- vllm/model_executor/kernels/linear/mixed_precision/zentorch.py
|
|
- vllm/model_executor/layers/fused_moe/experts/zentorch_moe.py
|
|
- tests/kernels/mamba/cpu/test_cpu_gdn_ops.py
|
|
- tests/kernels/mamba/test_cpu_short_conv.py
|
|
- tests/kernels/mamba/test_causal_conv1d.py
|
|
- tests/kernels/mamba/test_mamba_ssm.py
|
|
- vllm/v1/sample/ops/topk_topp_triton.py
|
|
- vllm/v1/sample/ops/topk_topp_sampler.py
|
|
- tests/v1/sample/test_topk_topp_sampler.py
|
|
commands:
|
|
- |
|
|
bash .buildkite/scripts/hardware_ci/run-cpu-test.sh 30m "
|
|
pytest -x -v -s --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB \
|
|
tests/kernels/attention/test_cpu_attn.py \
|
|
tests/v1/attention/test_group_head_counts.py \
|
|
tests/kernels/attention/test_amx_mla.py \
|
|
tests/kernels/test_deepseek_v4_cpu_kernels.py \
|
|
tests/kernels/moe/test_cpu_fused_moe.py \
|
|
tests/kernels/moe/test_cpu_quant_fused_moe.py \
|
|
tests/kernels/moe/test_zen_cpu_int8_moe.py \
|
|
tests/test_zentorch_version_pin.py \
|
|
tests/kernels/mamba/test_cpu_short_conv.py \
|
|
tests/kernels/test_onednn.py \
|
|
tests/kernels/test_cpu_fused_sampling.py \
|
|
tests/kernels/test_awq_int4_to_int8.py \
|
|
tests/kernels/quantization/test_cpu_fp8_scaled_mm.py \
|
|
tests/kernels/quantization/test_zen_da8w4.py \
|
|
tests/kernels/mamba/cpu/test_cpu_gdn_ops.py \
|
|
tests/kernels/mamba/test_causal_conv1d.py \
|
|
tests/kernels/mamba/test_mamba_ssm.py \
|
|
tests/v1/sample/test_topk_topp_sampler.py::TestTritonTopkTopp"
|
|
parallelism: 2
|
|
|
|
# Speculative decoding under a CPU platform. The unit tests already pass on
|
|
# CPU but no CPU job runs them; the e2e tests gate the engine path itself,
|
|
# which unit tests cannot reach.
|
|
- label: CPU-Spec Decode Tests
|
|
key: cpu-spec-decode-tests
|
|
depends_on: []
|
|
soft_fail: true
|
|
device: intel_cpu
|
|
no_plugin: true
|
|
source_file_dependencies:
|
|
- vllm/v1/spec_decode/
|
|
- vllm/v1/worker/cpu/
|
|
- vllm/v1/worker/cpu_model_runner.py
|
|
- vllm/v1/worker/gpu/spec_decode/
|
|
- vllm/v1/attention/backends/cpu_attn.py
|
|
- vllm/config/speculative.py
|
|
- vllm/model_executor/models/qwen3_5.py
|
|
- vllm/model_executor/models/qwen3_5_mtp.py
|
|
- vllm/model_executor/models/llama_eagle3.py
|
|
- vllm/model_executor/layers/mamba/gdn/qwen_gdn_linear_attn.py
|
|
- vllm/model_executor/layers/mamba/mamba_mixer2.py
|
|
- vllm/model_executor/layers/mamba/ops/cpu/
|
|
- tests/v1/e2e/test_cpu_spec_decode.py
|
|
- tests/v1/spec_decode/
|
|
- tests/v1/worker/
|
|
commands:
|
|
- |
|
|
bash .buildkite/scripts/hardware_ci/run-cpu-test.sh 30m "
|
|
pytest -x -v -s \
|
|
tests/v1/worker/test_gpu_target_dependent_ar_speculator.py \
|
|
tests/v1/worker/test_gpu_extract_hidden_states_speculator.py \
|
|
tests/v1/worker/test_gpu_batch_ordering.py \
|
|
tests/v1/worker/test_gpu_rejection_sampler_chunking.py \
|
|
tests/v1/worker/test_eagle3_aux_hidden_states_pp.py \
|
|
tests/v1/worker/test_spec_decode_embed_sharing_pp.py \
|
|
tests/v1/spec_decode/test_adaptive_verification.py \
|
|
tests/v1/spec_decode/test_dflash2.py \
|
|
tests/v1/spec_decode/test_dflash_causality.py \
|
|
tests/v1/spec_decode/test_eagle_draft_attn_metadata.py \
|
|
tests/v1/spec_decode/test_draft_attention_backend_override.py \
|
|
tests/v1/spec_decode/test_draft_moe_backend_override.py \
|
|
tests/v1/spec_decode/test_ngram.py \
|
|
tests/v1/spec_decode/test_llm_base_proposer_sampling.py
|
|
unset VLLM_CPU_CI_ENV
|
|
pytest -x -v -s tests/v1/e2e/test_cpu_spec_decode.py"
|
|
|
|
# Note: SDE can't be downloaded from CI host because of AWS WAF
|
|
# - label: CPU-Compatibility Tests
|
|
# depends_on: []
|
|
# device: intel_cpu
|
|
# no_plugin: true
|
|
# source_file_dependencies:
|
|
# - cmake/cpu_extension.cmake
|
|
# - setup.py
|
|
# - vllm/platforms/cpu.py
|
|
# commands:
|
|
# - |
|
|
# bash .buildkite/scripts/hardware_ci/run-cpu-test.sh 20m "
|
|
# bash .buildkite/scripts/hardware_ci/run-cpu-compatibility-test.sh"
|
|
|
|
- label: CPU-Language Generation and Pooling Model Tests Shard %N
|
|
key: cpu-language-generation-and-pooling-model-tests
|
|
depends_on: []
|
|
device: intel_cpu
|
|
no_plugin: true
|
|
source_file_dependencies:
|
|
- csrc/cpu/
|
|
- vllm/
|
|
- tests/models/language/generation/
|
|
- tests/models/language/pooling/
|
|
- tests/v1/e2e/test_cpu_linear_attn_chunked_prefix.py
|
|
commands:
|
|
- |
|
|
bash .buildkite/scripts/hardware_ci/run-cpu-test.sh 25m "
|
|
pytest -x -v -s tests/models/language/generation tests/models/language/pooling tests/v1/e2e/test_cpu_linear_attn_chunked_prefix.py -m cpu_model --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB"
|
|
parallelism: 3
|
|
|
|
- label: CPU-Quantization Model Tests
|
|
key: cpu-quantization-model-tests
|
|
depends_on: []
|
|
device: intel_cpu
|
|
no_plugin: true
|
|
source_file_dependencies:
|
|
- csrc/cpu/
|
|
- vllm/model_executor/layers/quantization/auto_gptq.py
|
|
- vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_int8.py
|
|
- vllm/model_executor/kernels/linear/mixed_precision/cpu.py
|
|
- vllm/model_executor/kernels/linear/scaled_mm/cpu.py
|
|
- vllm/model_executor/layers/fused_moe/experts/cpu_moe.py
|
|
- tests/quantization/test_compressed_tensors.py
|
|
- tests/quantization/test_cpu_wna16.py
|
|
- tests/quantization/test_cpu_w8a8.py
|
|
commands:
|
|
- |
|
|
bash .buildkite/scripts/hardware_ci/run-cpu-test.sh 45m "
|
|
pytest -x -v -s tests/quantization/test_compressed_tensors.py::test_compressed_tensors_w8a8_logprobs
|
|
pytest -x -v -s tests/quantization/test_cpu_wna16.py
|
|
pytest -x -v -s tests/quantization/test_cpu_w8a8.py"
|
|
|
|
- label: CPU-Distributed Tests (PP+TP)
|
|
key: cpu-distributed-tests-pp-tp
|
|
depends_on: []
|
|
device: intel_cpu
|
|
no_plugin: true
|
|
source_file_dependencies: &cpu_distributed_deps
|
|
- csrc/cpu/shm.cpp
|
|
- vllm/v1/worker/cpu_worker.py
|
|
- vllm/v1/worker/gpu_worker.py
|
|
- vllm/v1/worker/cpu_model_runner.py
|
|
- vllm/v1/worker/gpu_model_runner.py
|
|
- vllm/platforms/cpu.py
|
|
- vllm/distributed/parallel_state.py
|
|
- vllm/distributed/device_communicators/cpu_communicator.py
|
|
- .buildkite/scripts/hardware_ci/run-cpu-distributed-smoke-test.sh
|
|
commands:
|
|
- |
|
|
bash .buildkite/scripts/hardware_ci/run-cpu-test.sh 10m "
|
|
bash .buildkite/scripts/hardware_ci/run-cpu-distributed-smoke-test.sh tp_pp"
|
|
|
|
- label: CPU-Distributed Tests (DP+TP)
|
|
key: cpu-distributed-tests-dp-tp
|
|
depends_on: []
|
|
device: intel_cpu
|
|
no_plugin: true
|
|
source_file_dependencies: *cpu_distributed_deps
|
|
commands:
|
|
- |
|
|
bash .buildkite/scripts/hardware_ci/run-cpu-test.sh 10m "
|
|
bash .buildkite/scripts/hardware_ci/run-cpu-distributed-smoke-test.sh dp_tp"
|
|
|
|
- label: CPU-Multi-Modal Model Tests %N
|
|
key: cpu-multi-modal-model-tests-n
|
|
depends_on: []
|
|
device: intel_cpu
|
|
no_plugin: true
|
|
source_file_dependencies:
|
|
# - vllm/
|
|
- vllm/model_executor/layers/rotary_embedding
|
|
- tests/models/multimodal/generation/
|
|
commands:
|
|
- |
|
|
bash .buildkite/scripts/hardware_ci/run-cpu-test.sh 45m "
|
|
pytest -x -v -s tests/models/multimodal/generation --ignore=tests/models/multimodal/generation/test_pixtral.py --ignore=tests/models/multimodal/generation/test_qwen2_5_vl.py -m cpu_model --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB"
|
|
parallelism: 4
|
|
|
|
- label: CPU-Qwen2.5-VL Multimodal Tests
|
|
key: cpu-qwen2-5-vl-multimodal-tests
|
|
depends_on: []
|
|
device: intel_cpu
|
|
no_plugin: true
|
|
source_file_dependencies:
|
|
# - vllm/
|
|
- vllm/model_executor/layers/rotary_embedding
|
|
- tests/models/multimodal/generation/
|
|
commands:
|
|
- |
|
|
bash .buildkite/scripts/hardware_ci/run-cpu-test.sh 40m "
|
|
VLLM_CI_ENV=0 pytest -x -v -s tests/models/multimodal/generation/test_qwen2_5_vl.py"
|
|
|
|
- label: "Arm CPU Test Shard %N"
|
|
key: arm-cpu-test
|
|
depends_on:
|
|
- cpu-arm64-image-build
|
|
soft_fail: false
|
|
device: arm_cpu
|
|
no_plugin: true
|
|
commands:
|
|
- >-
|
|
bash .buildkite/scripts/hardware_ci/run-cpu-test-arm.sh
|
|
"$$BUILDKITE_PARALLEL_JOB"
|
|
"$REGISTRY/$REPO:$BUILDKITE_COMMIT-arm64-cpu"
|
|
parallelism: 3
|
|
|
|
- label: ":docker: Build Zen CPU image"
|
|
key: zen-cpu-image-build
|
|
# Reuse the shared `<repo>:<commit>-cpu` image that image-build-cpu publishes
|
|
# to public ECR, so Dockerfile.zen just layers on top instead of recompiling
|
|
# vLLM from source. If the pull fails, the build script still falls back to
|
|
# building the CPU base from source.
|
|
depends_on:
|
|
- image-build-cpu
|
|
soft_fail: true
|
|
agents:
|
|
queue: amd-cpu
|
|
source_file_dependencies:
|
|
- .buildkite/hardware_tests/cpu.yaml
|
|
- .buildkite/image_build/image_build_zen_cpu.sh
|
|
- docker/Dockerfile.zen
|
|
- docker/Dockerfile.cpu
|
|
- requirements/cpu.txt
|
|
- requirements/build/cpu.txt
|
|
- requirements/test/cpu.txt
|
|
- cmake/cpu_extension.cmake
|
|
- vllm/model_executor/layers/utils.py
|
|
- vllm/model_executor/kernels/linear/zentorch_utils.py
|
|
- vllm/model_executor/kernels/linear/scaled_mm/zentorch.py
|
|
- vllm/model_executor/kernels/linear/mixed_precision/zentorch.py
|
|
- vllm/platforms/cpu.py
|
|
- vllm/platforms/zen_cpu.py
|
|
- vllm/platforms/__init__.py
|
|
- tests/model_executor/test_cpu_unquantized_gemm_dispatch.py
|
|
- tests/test_zen_cpu_platform_detection.py
|
|
- tests/kernels/moe/test_zen_cpu_fused_moe.py
|
|
- tests/kernels/moe/test_zen_cpu_int8_moe.py
|
|
- vllm/v1/attention/backends/zentorch_sdpa.py
|
|
- tests/test_zentorch_version_pin.py
|
|
- vllm/v1/attention/backends/mla/prefill/zen_cpu_sdpa.py
|
|
- vllm/model_executor/layers/fused_moe/experts/zentorch_moe.py
|
|
- tests/kernels/quantization/test_zen_da8w4.py
|
|
commands:
|
|
- .buildkite/image_build/image_build_zen_cpu.sh "$REGISTRY" "$REPO" "$BUILDKITE_COMMIT"
|
|
env:
|
|
DOCKER_BUILDKIT: "1"
|
|
# Install zentorch directly (if-branch in Dockerfile.zen) instead of
|
|
# `uv pip install "vllm[zen]"`, which forces uv to re-resolve vLLM's full
|
|
# dependency closure and chokes on its transitive triton-cpu URL dependency.
|
|
# Keep this pin in sync with the `zen` extra in setup.py.
|
|
ZENTORCH_VERSION: "2.14.0.1"
|
|
retry:
|
|
automatic:
|
|
- exit_status: 1 # Transient Docker/BuildKit failure
|
|
limit: 1
|
|
- exit_status: -1 # Agent was lost
|
|
limit: 2
|
|
- exit_status: -10 # Agent was lost
|
|
limit: 2
|