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>
23 lines
577 B
YAML
23 lines
577 B
YAML
group: CUDA
|
|
depends_on:
|
|
- image-build
|
|
steps:
|
|
- label: Platform Tests (CUDA)
|
|
timeout_in_minutes: 15
|
|
source_file_dependencies:
|
|
- vllm/
|
|
- tests/cuda
|
|
commands:
|
|
- pytest -v -s cuda/test_cuda_context.py
|
|
- pytest -v -s cuda/test_platform_no_cuda_init.py
|
|
|
|
- label: Cudagraph
|
|
timeout_in_minutes: 20
|
|
source_file_dependencies:
|
|
- tests/v1/cudagraph
|
|
- vllm/v1/cudagraph_dispatcher.py
|
|
- vllm/config/compilation.py
|
|
- vllm/compilation
|
|
commands:
|
|
- pytest -v -s v1/cudagraph/test_cudagraph_dispatch.py
|
|
- pytest -v -s v1/cudagraph/test_cudagraph_mode.py |