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:
8
third_party/vllm/examples/online_serving/structured_outputs/pyproject.toml
vendored
Normal file
8
third_party/vllm/examples/online_serving/structured_outputs/pyproject.toml
vendored
Normal file
@@ -0,0 +1,8 @@
|
||||
[project]
|
||||
name = "examples-online-structured-outputs"
|
||||
requires-python = ">=3.10, <3.14"
|
||||
dependencies = ["openai==1.78.1", "pydantic==2.11.4"]
|
||||
version = "0.0.0"
|
||||
|
||||
[project.scripts]
|
||||
structured-outputs = "structured_outputs:main"
|
||||
Reference in New Issue
Block a user