Kevin H. LuuandClaude Opus 5.5
206e45d470
Signed-off-by: khluu <khluu000@gmail.com> Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
92 lines
3.2 KiB
YAML
92 lines
3.2 KiB
YAML
group: Attention
|
|
depends_on:
|
|
- image-build
|
|
steps:
|
|
- label: ":nvidia: (H100) V1 Attention"
|
|
key: v1-attention-h100-mi300
|
|
automatic_shard: true
|
|
timeout_in_minutes: 85
|
|
device: h100
|
|
source_file_dependencies:
|
|
- vllm/config/attention.py
|
|
- vllm/model_executor/layers/attention
|
|
- vllm/v1/attention
|
|
- tests/v1/attention
|
|
commands:
|
|
- pytest -v -s v1/attention
|
|
mirror:
|
|
amd:
|
|
label: ":amd: (MI300) V1 Attention Shard %N"
|
|
dind: false
|
|
device: mi300_1
|
|
timeout_in_minutes: 125
|
|
# automatic_shard covers NVIDIA steps only; the mirror keeps its
|
|
# fixed pytest shards.
|
|
parallelism: 2
|
|
commands:
|
|
- pytest -v -s v1/attention --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT
|
|
depends_on:
|
|
- image-build-amd
|
|
source_file_dependencies:
|
|
- vllm/config/attention.py
|
|
- vllm/model_executor/layers/attention
|
|
- vllm/v1/attention
|
|
- tests/v1/attention
|
|
- vllm/_aiter_ops.py
|
|
- vllm/envs.py
|
|
- vllm/platforms/rocm.py
|
|
- vllm/models/deepseek_v32/amd/rocm.py
|
|
commands:
|
|
- pytest -v -s v1/attention --ignore=v1/attention/test_sparse_mla_backends.py --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT
|
|
- VLLM_ROCM_USE_AITER=1 pytest -v -s v1/attention/test_sparse_mla_backends.py --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT
|
|
|
|
- label: ":nvidia: (B200) V1 Attention"
|
|
key: v1-attention-b200
|
|
automatic_shard: true
|
|
timeout_in_minutes: 80
|
|
device: b200-k8s
|
|
source_file_dependencies:
|
|
- vllm/config/attention.py
|
|
- vllm/model_executor/layers/attention
|
|
- vllm/v1/attention
|
|
- tests/v1/attention
|
|
commands:
|
|
- pytest -v -s v1/attention
|
|
mirror:
|
|
amd:
|
|
label: ":amd: (MI355 DPX) V1 Attention Shard %N"
|
|
dind: false
|
|
device: mi355_dpx
|
|
timeout_in_minutes: 125
|
|
# automatic_shard covers NVIDIA steps only; the mirror keeps its
|
|
# fixed pytest shards.
|
|
parallelism: 2
|
|
depends_on:
|
|
- image-build-amd
|
|
source_file_dependencies:
|
|
- vllm/config/attention.py
|
|
- vllm/model_executor/layers/attention
|
|
- vllm/v1/attention
|
|
- tests/v1/attention
|
|
- vllm/_aiter_ops.py
|
|
- vllm/envs.py
|
|
- vllm/platforms/rocm.py
|
|
- vllm/models/deepseek_v32/amd/rocm.py
|
|
commands:
|
|
- pytest -v -s v1/attention --ignore=v1/attention/test_mla_backends.py --ignore=v1/attention/test_sparse_mla_backends.py --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT
|
|
- VLLM_ROCM_USE_AITER=1 pytest -v -s v1/attention/test_mla_backends.py v1/attention/test_sparse_mla_backends.py --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT
|
|
|
|
- label: ":nvidia: (DGX) Spark FlashInfer NVFP4 XQA"
|
|
key: flashinfer-nvfp4-xqa-dgx-spark
|
|
timeout_in_minutes: 30
|
|
device: dgx-spark
|
|
optional: true
|
|
num_devices: 1
|
|
depends_on:
|
|
- arm64-image-build
|
|
source_file_dependencies:
|
|
- vllm/v1/attention/backends/flashinfer.py
|
|
- tests/v1/attention/test_attention_backends.py
|
|
commands:
|
|
- pytest -v -s v1/attention/test_attention_backends.py -k test_flashinfer_xqa_nvfp4_decode_correctness
|