diff --git a/.buildkite/intel_jobs/benchmarks_intel.yaml b/.buildkite/intel_jobs/benchmarks_intel.yaml new file mode 100644 index 0000000000..9ce373e4f4 --- /dev/null +++ b/.buildkite/intel_jobs/benchmarks_intel.yaml @@ -0,0 +1,26 @@ +group: Benchmarks +depends_on: + - image-build-xpu +steps: +- label: Benchmarks CLI Test + key: benchmarks-cli-test + timeout_in_minutes: 40 + device: intel_gpu + agent_tags: + label: production + gpu: 1+ + mem: 16+ + no_plugin: true + working_dir: "." + env: + REGISTRY: "public.ecr.aws/q9t5s3a7" + REPO: "vllm-ci-test-repo" + VLLM_TEST_DEVICE: "xpu" + source_file_dependencies: + - vllm/ + - tests/benchmarks/ + commands: + - >- + bash .buildkite/scripts/hardware_ci/run-intel-test.sh + 'cd tests && + pytest -v -s benchmarks/' diff --git a/.buildkite/intel_jobs/engine_intel.yaml b/.buildkite/intel_jobs/engine_intel.yaml index d1dc95b1d4..5f9357b2a7 100644 --- a/.buildkite/intel_jobs/engine_intel.yaml +++ b/.buildkite/intel_jobs/engine_intel.yaml @@ -2,6 +2,44 @@ group: Engine Intel depends_on: - image-build-xpu steps: +- label: Engine + key: engine + timeout_in_minutes: 40 + device: intel_gpu + agent_tags: + label: production + gpu: 1+ + mem: 16+ + no_plugin: true + working_dir: "." + env: + REGISTRY: "public.ecr.aws/q9t5s3a7" + REPO: "vllm-ci-test-repo" + VLLM_TEST_DEVICE: "xpu" + source_file_dependencies: + - vllm/compilation/ + - vllm/config/ + - vllm/engine/ + - vllm/entrypoints/logger.py + - vllm/envs.py + - vllm/logger.py + - vllm/logging_utils/ + - vllm/platforms/ + - vllm/sequence.py + - vllm/triton_utils/ + - vllm/utils/ + - tests/engine + - tests/test_sequence + - tests/test_config + - tests/test_logger + - tests/test_vllm_port + - tests/test_jit_monitor.py + commands: + - >- + bash .buildkite/scripts/hardware_ci/run-intel-test.sh + 'cd tests && + pytest -v -s engine/test_arg_utils.py test_sequence.py test_logger.py test_vllm_port.py test_jit_monitor.py' + - label: Engine (1 GPU) timeout_in_minutes: 30 device: intel_gpu @@ -23,3 +61,41 @@ steps: bash .buildkite/scripts/hardware_ci/run-intel-test.sh 'cd tests && pytest -v -s v1/engine --ignore v1/engine/test_preprocess_error_handling.py' + +- label: V1 e2e (2 GPUs) + timeout_in_minutes: 30 + device: intel_gpu + agent_tags: + label: production + gpu: 2+ + mem: 16+ + no_plugin: true + working_dir: "." + env: + REGISTRY: "public.ecr.aws/q9t5s3a7" + REPO: "vllm-ci-test-repo" + VLLM_TEST_DEVICE: "xpu" + source_file_dependencies: + - vllm/compilation/ + - vllm/config/ + - vllm/distributed/ + - vllm/engine/ + - vllm/envs.py + - vllm/forward_context.py + - vllm/inputs/ + - vllm/logger.py + - vllm/logging_utils/ + - vllm/model_executor/ + - vllm/multimodal/ + - vllm/platforms/ + - vllm/sampling_params.py + - vllm/transformers_utils/ + - vllm/triton_utils/ + - vllm/utils/ + - vllm/v1/ + - tests/v1/e2e/spec_decode + commands: + - >- + bash .buildkite/scripts/hardware_ci/run-intel-test.sh + 'cd tests && + pytest -v -s v1/e2e/spec_decode/test_spec_decode.py -k "tensor_parallelism"' diff --git a/.buildkite/intel_jobs/model_executor_intel.yaml b/.buildkite/intel_jobs/model_executor_intel.yaml new file mode 100644 index 0000000000..14a853544e --- /dev/null +++ b/.buildkite/intel_jobs/model_executor_intel.yaml @@ -0,0 +1,33 @@ +group: Model Executor Intel +depends_on: + - image-build-xpu +steps: +- label: Model Executor (Intel) + key: model-executor-intel + timeout_in_minutes: 45 + device: intel_gpu + agent_tags: + label: production + gpu: 1+ + mem: 24+ + no_plugin: true + working_dir: "." + env: + REGISTRY: "public.ecr.aws/q9t5s3a7" + REPO: "vllm-ci-test-repo" + VLLM_TEST_DEVICE: "xpu" + source_file_dependencies: + - vllm/engine/arg_utils.py + - vllm/config/model.py + - vllm/model_executor + - tests/model_executor + commands: + - >- + bash .buildkite/scripts/hardware_ci/run-intel-test.sh + 'apt-get update && apt-get install -y curl libsodium23 && + pip3 install tensorizer==2.10.1 && + pip3 install runai-model-streamer[s3,gcs,azure]\>=0.15.7 && + export VLLM_WORKER_MULTIPROC_METHOD=spawn && + export PYTHONFAULTHANDLER=1 && + cd tests && + pytest -v -s model_executor -m "not slow_test" --ignore="model_executor/layers/test_rocm_unquantized_gemm.py" --deselect="tests/model_executor/model_loader/test_reload.py::test_kv_scale_reload"' diff --git a/.buildkite/intel_jobs/model_runner_v2_intel.yaml b/.buildkite/intel_jobs/model_runner_v2_intel.yaml index 0311b5dffb..43ab989fbb 100644 --- a/.buildkite/intel_jobs/model_runner_v2_intel.yaml +++ b/.buildkite/intel_jobs/model_runner_v2_intel.yaml @@ -8,7 +8,7 @@ steps: agent_tags: label: production gpu: 2+ - mem: 16+ + mem: 24+ no_plugin: true working_dir: "." env: @@ -28,7 +28,9 @@ steps: 'export VLLM_USE_V2_MODEL_RUNNER=1 && cd tests && pytest -v -s v1/engine/test_llm_engine.py -k "not test_engine_metrics" && + pytest -v -s v1/e2e/general/test_context_length.py && ENFORCE_EAGER=1 pytest -v -s v1/e2e/general/test_async_scheduling.py -k "not ngram" && + 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" && pytest -v -s v1/e2e/general/test_min_tokens.py' - label: Model Runner V2 Examples (Intel) @@ -60,3 +62,55 @@ steps: python3 basic/offline_inference/generate.py --model facebook/opt-125m && python3 generate/multimodal/vision_language_offline.py --seed 0 && python3 features/automatic_prefix_caching/prefix_caching_offline.py' + +- label: Model Runner V2 Distributed (2 GPUs) + timeout_in_minutes: 50 + device: intel_gpu + agent_tags: + label: production + gpu: 2+ + mem: 16+ + no_plugin: true + working_dir: "." + env: + REGISTRY: "public.ecr.aws/q9t5s3a7" + REPO: "vllm-ci-test-repo" + VLLM_TEST_DEVICE: "xpu" + 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 + commands: + - >- + bash .buildkite/scripts/hardware_ci/run-intel-test.sh + 'export VLLM_USE_V2_MODEL_RUNNER=1 && + cd tests && + TARGET_TEST_SUITE=L4 pytest -v -s basic_correctness/test_basic_correctness.py -m "distributed\(num_gpus=2\)" -k "not ray and not True"' + +- label: Model Runner V2 Spec Decode + timeout_in_minutes: 50 + device: intel_gpu + agent_tags: + label: production + gpu: 1+ + mem: 24+ + no_plugin: true + working_dir: "." + env: + REGISTRY: "public.ecr.aws/q9t5s3a7" + REPO: "vllm-ci-test-repo" + VLLM_TEST_DEVICE: "xpu" + 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/e2e/spec_decode/test_spec_decode.py + commands: + - >- + bash .buildkite/scripts/hardware_ci/run-intel-test.sh + 'export VLLM_USE_V2_MODEL_RUNNER=1 && + cd tests && + pytest -v -s v1/spec_decode/test_synthetic_rejection_sampler_utils.py' diff --git a/.buildkite/intel_jobs/samplers_intel.yaml b/.buildkite/intel_jobs/samplers_intel.yaml new file mode 100644 index 0000000000..acd9480320 --- /dev/null +++ b/.buildkite/intel_jobs/samplers_intel.yaml @@ -0,0 +1,29 @@ +group: Samplers Intel +depends_on: + - image-build-xpu +steps: +- label: Samplers Test (FlashInfer) + key: samplers-test-flashinfer-intel + timeout_in_minutes: 40 + device: intel_gpu + agent_tags: + label: production + gpu: 1+ + mem: 24+ + no_plugin: true + working_dir: "." + env: + REGISTRY: "public.ecr.aws/q9t5s3a7" + REPO: "vllm-ci-test-repo" + VLLM_TEST_DEVICE: "xpu" + source_file_dependencies: + - vllm/model_executor/layers + - vllm/sampling_metadata.py + - tests/samplers + - tests/conftest.py + - vllm/entrypoints/generate/beam_search + commands: + - >- + bash .buildkite/scripts/hardware_ci/run-intel-test.sh + 'cd tests && + VLLM_USE_FLASHINFER_SAMPLER=1 pytest -v -s samplers'