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:
13
third_party/vllm/docs/deployment/docker.md
vendored
Normal file
13
third_party/vllm/docs/deployment/docker.md
vendored
Normal file
@@ -0,0 +1,13 @@
|
||||
---
|
||||
toc_depth: 2
|
||||
---
|
||||
|
||||
# Using Docker
|
||||
|
||||
## Pre-built images
|
||||
|
||||
--8<-- "docs/getting_started/installation/gpu.md:pre-built-images"
|
||||
|
||||
## Build image from source
|
||||
|
||||
--8<-- "docs/getting_started/installation/gpu.md:build-image-from-source"
|
||||
Reference in New Issue
Block a user