Add vLLM v0.18.1 source tree with KV transfer abort fix
third_party/vllm/ now tracked in git for direct patch management.
Based on vLLM v0.18.1 release with one patch applied:
vllm/v1/core/sched/scheduler.py:
Replace fatal assert with graceful skip when KV transfer callback
arrives for an already-aborted request during PD disaggregated serving.
Future vLLM modifications should be made directly in third_party/vllm/
and committed normally. The patches/ directory is kept as documentation
of what changed from upstream.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
25
third_party/vllm/.buildkite/test_areas/attention.yaml
vendored
Normal file
25
third_party/vllm/.buildkite/test_areas/attention.yaml
vendored
Normal file
@@ -0,0 +1,25 @@
|
||||
group: Attention
|
||||
depends_on:
|
||||
- image-build
|
||||
steps:
|
||||
- label: V1 attention (H100)
|
||||
timeout_in_minutes: 30
|
||||
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
|
||||
|
||||
- label: V1 attention (B200)
|
||||
timeout_in_minutes: 30
|
||||
device: b200
|
||||
source_file_dependencies:
|
||||
- vllm/config/attention.py
|
||||
- vllm/model_executor/layers/attention
|
||||
- vllm/v1/attention
|
||||
- tests/v1/attention
|
||||
commands:
|
||||
- pytest -v -s v1/attention
|
||||
Reference in New Issue
Block a user