mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2026-04-23 00:17:25 +08:00
[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:
@@ -424,7 +424,7 @@ class LLMEngine:
|
||||
else:
|
||||
err, data = self.zmq_server.receive_pyobj_once(block)
|
||||
if err is not None:
|
||||
llm_logger.error("Engine stops inserting zmq task into scheduler")
|
||||
llm_logger.error("Engine stops inserting zmq task into scheduler, err:{err}")
|
||||
break
|
||||
|
||||
request, insert_task = None, []
|
||||
|
||||
Reference in New Issue
Block a user