[TRTLLM-12622][feat] Add native post-processing hook to trtllm-serve#15239

Open

xwang233 wants to merge 19 commits into

NVIDIA:mainfrom

xwang233:trtllm-12622-post-processor-hook

Commits on Jun 11, 2026

[TRTLLM-12622][chore] Address post-processor hook review feedback
xwang233
committed

Commits on Jun 15, 2026

[TRTLLM-12622][chore] Fail-fast hook registration + review fixes
xwang233
committed
[TRTLLM-12622][refactor] Scope post-processing hook to the LLM instance
xwang233
committed
Merge remote-tracking branch 'origin/main' into trtllm-12622-post-processor-hook
xwang233
committed
[TRTLLM-12622][chore] Trim verbose comments and a redundant test
xwang233
committed
[TRTLLM-12622][fix] Run post-processing hook regardless of detokenize flag
xwang233
committed
[TRTLLM-12622][fix] Withhold all client channels on suppress/terminate
xwang233
committed
[TRTLLM-12622][doc] Clarify per-chunk withholding semantics
xwang233
committed
[TRTLLM-12622][fix] Fail closed on hook errors; enum verdict actions
xwang233
committed

Commits on Jun 16, 2026

[TRTLLM-12622][test] Register post-processor hook unit tests in L0 A10
xwang233
committed

Commits on Jun 22, 2026

Commits on Jun 23, 2026