[ci] Route 28 gpu_1_queue tests to h200_35gb queue (#43030)
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
co-authored by
Claude Opus 4.6
parent
fab07e4d0f
commit
6e889b582b
@@ -60,6 +60,7 @@ steps:
|
||||
- image-build-amd
|
||||
|
||||
- label: e2e Core (1 GPU)
|
||||
device: h200_35gb
|
||||
key: e2e-core-1-gpu
|
||||
timeout_in_minutes: 30
|
||||
source_file_dependencies:
|
||||
|
||||
@@ -88,6 +88,7 @@ steps:
|
||||
- image-build-amd
|
||||
|
||||
- label: Entrypoints Integration (API Server 2)
|
||||
device: h200_35gb
|
||||
key: entrypoints-integration-api-server-2
|
||||
timeout_in_minutes: 130
|
||||
working_dir: "/vllm-workspace/tests"
|
||||
@@ -108,6 +109,7 @@ steps:
|
||||
- image-build-amd
|
||||
|
||||
- label: Entrypoints Integration (Speech to Text)
|
||||
device: h200_35gb
|
||||
key: entrypoints-integration-speech_to_text
|
||||
timeout_in_minutes: 50
|
||||
working_dir: "/vllm-workspace/tests"
|
||||
|
||||
@@ -3,6 +3,7 @@ depends_on:
|
||||
- image-build
|
||||
steps:
|
||||
- label: LM Eval Small Models
|
||||
device: h200_35gb
|
||||
key: lm-eval-small-models
|
||||
timeout_in_minutes: 75
|
||||
source_file_dependencies:
|
||||
@@ -152,6 +153,7 @@ steps:
|
||||
- pytest -s -v evals/gpt_oss/test_gpqa_correctness.py --config-list-file=configs/models-b200.txt
|
||||
|
||||
- label: MRCR Eval Small Models
|
||||
device: h200_35gb
|
||||
timeout_in_minutes: 30
|
||||
source_file_dependencies:
|
||||
- tests/evals/mrcr/
|
||||
|
||||
@@ -3,6 +3,7 @@ depends_on:
|
||||
- image-build
|
||||
steps:
|
||||
- label: LoRA %N
|
||||
device: h200_35gb
|
||||
key: lora
|
||||
timeout_in_minutes: 30
|
||||
source_file_dependencies:
|
||||
|
||||
@@ -3,6 +3,7 @@ depends_on:
|
||||
- image-build
|
||||
steps:
|
||||
- label: V1 Spec Decode
|
||||
device: h200_35gb
|
||||
key: v1-spec-decode
|
||||
timeout_in_minutes: 30
|
||||
source_file_dependencies:
|
||||
@@ -165,6 +166,7 @@ steps:
|
||||
working_dir: "/vllm-workspace/tests" # optional
|
||||
|
||||
- label: Examples
|
||||
device: h200_35gb
|
||||
key: examples
|
||||
timeout_in_minutes: 45
|
||||
working_dir: "/vllm-workspace/examples"
|
||||
@@ -235,6 +237,7 @@ steps:
|
||||
- bash standalone_tests/python_only_compile.sh
|
||||
|
||||
- label: Async Engine, Inputs, Utils, Worker
|
||||
device: h200_35gb
|
||||
key: async-engine-inputs-utils-worker
|
||||
timeout_in_minutes: 50
|
||||
source_file_dependencies:
|
||||
@@ -366,6 +369,7 @@ steps:
|
||||
- pytest -v -s v1/determinism/test_nvfp4_batch_invariant.py
|
||||
|
||||
- label: Acceptance Length Test (Large Models) # optional
|
||||
device: h200_35gb
|
||||
key: acceptance-length-test-large-models
|
||||
timeout_in_minutes: 25
|
||||
gpu: h100
|
||||
|
||||
@@ -3,6 +3,7 @@ depends_on:
|
||||
- image-build
|
||||
steps:
|
||||
- label: Model Executor
|
||||
device: h200_35gb
|
||||
key: model-executor
|
||||
timeout_in_minutes: 35
|
||||
source_file_dependencies:
|
||||
|
||||
@@ -3,6 +3,7 @@ depends_on:
|
||||
- image-build
|
||||
steps:
|
||||
- label: Model Runner V2 Core Tests
|
||||
device: h200_35gb
|
||||
key: model-runner-v2-core-tests
|
||||
timeout_in_minutes: 45
|
||||
source_file_dependencies:
|
||||
@@ -26,6 +27,7 @@ steps:
|
||||
- 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"
|
||||
|
||||
- label: Model Runner V2 Examples
|
||||
device: h200_35gb
|
||||
key: model-runner-v2-examples
|
||||
timeout_in_minutes: 45
|
||||
working_dir: "/vllm-workspace/examples"
|
||||
@@ -99,6 +101,7 @@ steps:
|
||||
- pytest -v -s distributed/test_pp_cudagraph.py -k "not ray"
|
||||
|
||||
- label: Model Runner V2 Spec Decode
|
||||
device: h200_35gb
|
||||
key: model-runner-v2-spec-decode
|
||||
timeout_in_minutes: 30
|
||||
working_dir: "/vllm-workspace/tests"
|
||||
|
||||
@@ -18,6 +18,7 @@ steps:
|
||||
torch_nightly: {}
|
||||
|
||||
- label: Basic Models Tests (Extra Initialization) %N
|
||||
device: h200_35gb
|
||||
key: basic-models-tests-extra-initialization
|
||||
timeout_in_minutes: 45
|
||||
source_file_dependencies:
|
||||
@@ -34,6 +35,7 @@ steps:
|
||||
torch_nightly: {}
|
||||
|
||||
- label: Basic Models Tests (Other)
|
||||
device: h200_35gb
|
||||
key: basic-models-tests-other
|
||||
timeout_in_minutes: 45
|
||||
source_file_dependencies:
|
||||
@@ -58,6 +60,7 @@ steps:
|
||||
- pytest -v -s models/test_utils.py models/test_vision.py
|
||||
|
||||
- label: Transformers Nightly Models
|
||||
device: h200_35gb
|
||||
key: transformers-nightly-models
|
||||
working_dir: "/vllm-workspace/"
|
||||
optional: true
|
||||
@@ -74,6 +77,7 @@ steps:
|
||||
- VLLM_WORKER_MULTIPROC_METHOD=spawn python3 examples/generate/multimodal/audio_language_offline.py --model-type whisper
|
||||
|
||||
- label: Transformers Backward Compatibility Models Test
|
||||
device: h200_35gb
|
||||
key: transformers-backward-compatibility-models-test
|
||||
working_dir: "/vllm-workspace/"
|
||||
optional: true
|
||||
|
||||
@@ -34,6 +34,7 @@ steps:
|
||||
torch_nightly: {}
|
||||
|
||||
- label: Language Models Tests (Hybrid) %N
|
||||
device: h200_35gb
|
||||
key: language-models-tests-hybrid
|
||||
timeout_in_minutes: 75
|
||||
source_file_dependencies:
|
||||
@@ -59,6 +60,7 @@ steps:
|
||||
- pytest -v -s models/language/generation -m hybrid_model --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB
|
||||
|
||||
- label: Language Models Test (Extended Generation) # 80min
|
||||
device: h200_35gb
|
||||
key: language-models-test-extended-generation
|
||||
timeout_in_minutes: 110
|
||||
optional: true
|
||||
@@ -84,6 +86,7 @@ steps:
|
||||
- pytest -v -s models/language/generation_ppl_test
|
||||
|
||||
- label: Language Models Test (Extended Pooling) # 36min
|
||||
device: h200_35gb
|
||||
key: language-models-test-extended-pooling
|
||||
timeout_in_minutes: 50
|
||||
optional: true
|
||||
|
||||
@@ -38,6 +38,7 @@ steps:
|
||||
- image-build-amd
|
||||
|
||||
- label: "Multi-Modal Models (Standard) 3: llava + qwen2_vl"
|
||||
device: h200_35gb
|
||||
key: multi-modal-models-standard-3-llava-qwen2-vl
|
||||
timeout_in_minutes: 45
|
||||
source_file_dependencies:
|
||||
@@ -54,6 +55,7 @@ steps:
|
||||
- image-build-amd
|
||||
|
||||
- label: "Multi-Modal Models (Standard) 4: other + whisper"
|
||||
device: h200_35gb
|
||||
key: multi-modal-models-standard-4-other-whisper
|
||||
timeout_in_minutes: 45
|
||||
source_file_dependencies:
|
||||
@@ -92,6 +94,7 @@ steps:
|
||||
- pytest -v -s models/multimodal/processing/test_tensor_schema.py
|
||||
|
||||
- label: Multi-Modal Accuracy Eval (Small Models) # 50min
|
||||
device: h200_35gb
|
||||
key: multi-modal-accuracy-eval-small-models
|
||||
timeout_in_minutes: 70
|
||||
working_dir: "/vllm-workspace/.buildkite/lm-eval-harness"
|
||||
@@ -120,6 +123,7 @@ steps:
|
||||
- image-build-amd
|
||||
|
||||
- label: Multi-Modal Models (Extended Generation 2)
|
||||
device: h200_35gb
|
||||
key: multi-modal-models-extended-generation-2
|
||||
optional: true
|
||||
source_file_dependencies:
|
||||
@@ -130,6 +134,7 @@ steps:
|
||||
- pytest -v -s models/multimodal/generation/test_common.py -m 'split(group=0) and not core_model'
|
||||
|
||||
- label: Multi-Modal Models (Extended Generation 3)
|
||||
device: h200_35gb
|
||||
key: multi-modal-models-extended-generation-3
|
||||
optional: true
|
||||
source_file_dependencies:
|
||||
|
||||
@@ -3,6 +3,7 @@ depends_on:
|
||||
- image-build
|
||||
steps:
|
||||
- label: PyTorch Compilation Unit Tests
|
||||
device: h200_35gb
|
||||
key: pytorch-compilation-unit-tests
|
||||
timeout_in_minutes: 10
|
||||
source_file_dependencies:
|
||||
|
||||
@@ -3,6 +3,7 @@ depends_on:
|
||||
- image-build
|
||||
steps:
|
||||
- label: Samplers Test
|
||||
device: h200_35gb
|
||||
key: samplers-test
|
||||
timeout_in_minutes: 75
|
||||
source_file_dependencies:
|
||||
|
||||
Reference in New Issue
Block a user