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>
26 lines
706 B
YAML
26 lines
706 B
YAML
group: Weight Loading
|
|
depends_on:
|
|
- image-build
|
|
steps:
|
|
- label: Weight Loading Multiple GPU # 33min
|
|
timeout_in_minutes: 45
|
|
working_dir: "/vllm-workspace/tests"
|
|
num_devices: 2
|
|
optional: true
|
|
source_file_dependencies:
|
|
- vllm/
|
|
- tests/weight_loading
|
|
commands:
|
|
- bash weight_loading/run_model_weight_loading_test.sh -c weight_loading/models.txt
|
|
|
|
# - label: Weight Loading Multiple GPU - Large Models # optional
|
|
# working_dir: "/vllm-workspace/tests"
|
|
# num_devices: 2
|
|
# device: a100
|
|
# optional: true
|
|
# source_file_dependencies:
|
|
# - vllm/
|
|
# - tests/weight_loading
|
|
# commands:
|
|
# - bash weight_loading/run_model_weight_loading_test.sh -c weight_loading/models-large.txt
|