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:
16
third_party/vllm/.github/workflows/matchers/mypy.json
vendored
Normal file
16
third_party/vllm/.github/workflows/matchers/mypy.json
vendored
Normal file
@@ -0,0 +1,16 @@
|
||||
{
|
||||
"problemMatcher": [
|
||||
{
|
||||
"owner": "mypy",
|
||||
"pattern": [
|
||||
{
|
||||
"regexp": "^(.+):(\\d+):\\s(error|warning):\\s(.+)$",
|
||||
"file": 1,
|
||||
"line": 2,
|
||||
"severity": 3,
|
||||
"message": 4
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
Reference in New Issue
Block a user