[CI] Shard V1 Attention automatically instead of by fixed pytest shards (#61200)

Signed-off-by: khluu <khluu000@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Kevin H. Luu
2026-10-13 02:24:06 -07:00
committed by GitHub
co-authored by Claude Opus 5.5
parent 656d0d4506
commit 206e45d470
+14 -6
View File
@@ -2,8 +2,9 @@ group: Attention
depends_on:
- image-build
steps:
- label: ":nvidia: (H100) V1 Attention Shard %N"
- label: ":nvidia: (H100) V1 Attention"
key: v1-attention-h100-mi300
automatic_shard: true
timeout_in_minutes: 85
device: h100
source_file_dependencies:
@@ -12,14 +13,18 @@ steps:
- vllm/v1/attention
- tests/v1/attention
commands:
- pytest -v -s v1/attention --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT
parallelism: 2
- 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:
@@ -35,8 +40,9 @@ steps:
- 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 Shard %N"
- label: ":nvidia: (B200) V1 Attention"
key: v1-attention-b200
automatic_shard: true
timeout_in_minutes: 80
device: b200-k8s
source_file_dependencies:
@@ -45,14 +51,16 @@ steps:
- vllm/v1/attention
- tests/v1/attention
commands:
- pytest -v -s v1/attention --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT
parallelism: 2
- 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: