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>
BIN
third_party/vllm/docs/assets/design/prefix_caching/example-time-1.png
vendored
Normal file
|
After Width: | Height: | Size: 47 KiB |
BIN
third_party/vllm/docs/assets/design/prefix_caching/example-time-3.png
vendored
Normal file
|
After Width: | Height: | Size: 50 KiB |
BIN
third_party/vllm/docs/assets/design/prefix_caching/example-time-4.png
vendored
Normal file
|
After Width: | Height: | Size: 59 KiB |
BIN
third_party/vllm/docs/assets/design/prefix_caching/example-time-5.png
vendored
Normal file
|
After Width: | Height: | Size: 54 KiB |
BIN
third_party/vllm/docs/assets/design/prefix_caching/example-time-6.png
vendored
Normal file
|
After Width: | Height: | Size: 54 KiB |
BIN
third_party/vllm/docs/assets/design/prefix_caching/example-time-7.png
vendored
Normal file
|
After Width: | Height: | Size: 55 KiB |
BIN
third_party/vllm/docs/assets/design/prefix_caching/free.png
vendored
Normal file
|
After Width: | Height: | Size: 18 KiB |
BIN
third_party/vllm/docs/assets/design/prefix_caching/overview.png
vendored
Normal file
|
After Width: | Height: | Size: 32 KiB |