[Feature] General support for logprobs (#2974)

* [Feature] support logprobs in chat/completions and completions endpoints

* Temporarily comment out text_offset due to incorrect logic

* Clean up temporary debug prints

* [Feature] support logprobs in offline mode via SamplingParams

* fix: serialize Logprob as dict before zmq send to fix msgpack error

* refactor: remove redundant methods to simplify codebase

* Fix missing fields in CompletionOutput.to_dict affecting msgpack serialization

* refactor: centralize param validation in engine_client to reduce duplication

* revert: rollback changes in offline_demo.py

* revert: rollback changes in offline_demo.py

* [bugfix] fix parameter validation for logprobs

* [bugfix] fix parameter validation for logprobs

* [bugfix] fix parameter validation for logprobs

* [bugfix] fix parameter validation for logprobs

---------

Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
This commit is contained in:
SunLei
2025-07-31 20:25:56 +08:00
committed by GitHub
parent fe17410f9c
commit dade19d7a4
10 changed files with 330 additions and 44 deletions

View File

@@ -394,6 +394,7 @@ class TokenProcessor:
logprobs=[topk_logprobs],
sampled_token_ranks=[sampled_rank],
)
if token_id in task.eos_token_ids or is_prefill or recovery_stop:
result.finished = True
if recovery_stop: