Gahow Wang
445e491123
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>
18 lines
519 B
YAML
18 lines
519 B
YAML
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
|