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:
17
third_party/vllm/.buildkite/test_areas/model_executor.yaml
vendored
Normal file
17
third_party/vllm/.buildkite/test_areas/model_executor.yaml
vendored
Normal file
@@ -0,0 +1,17 @@
|
||||
group: Model Executor
|
||||
depends_on:
|
||||
- image-build
|
||||
steps:
|
||||
- label: Model Executor
|
||||
timeout_in_minutes: 35
|
||||
source_file_dependencies:
|
||||
- vllm/engine/arg_utils.py
|
||||
- vllm/config/model.py
|
||||
- vllm/model_executor
|
||||
- tests/model_executor
|
||||
- tests/entrypoints/openai/test_tensorizer_entrypoint.py
|
||||
commands:
|
||||
- apt-get update && apt-get install -y curl libsodium23
|
||||
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
|
||||
- pytest -v -s model_executor
|
||||
- pytest -v -s entrypoints/openai/test_tensorizer_entrypoint.py
|
||||
Reference in New Issue
Block a user