Dao007forever 3f5bd482f5 [Bugfix][KV Transfer][NIXL] Notify P node on pre-admission rejection to free stranded KV blocks (#41269)

2026-05-09 22:52:09 -07:00

..

__init__.py

[Refactor] [10/N] to simplify the vLLM openai completion serving architecture (#32369)

2026-01-15 07:41:34 +00:00

api_router.py

[openapi server] log exception in exception handler(2/N) (#36201)

2026-03-10 20:16:30 -07:00

protocol.py

[Core] Replace routing replay with device cache and async D2H pipeline (#39917)

2026-05-07 11:24:56 -07:00

serving.py

[Bugfix][KV Transfer][NIXL] Notify P node on pre-admission rejection to free stranded KV blocks (#41269)

2026-05-09 22:52:09 -07:00