apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-04 08:16:42 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[Feature] General support for logprobs (#2974)

Browse Source 
* [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
Download Patch File Download Diff File Expand all files Collapse all files

17
fastdeploy/entrypoints/openai/protocol.py
View File

@@ -18,7 +18,7 @@ from __future__ import annotations
import json
import time
from typing import Any, List, Literal, Optional, Union
from typing import Any, Dict, List, Literal, Optional, Union
from pydantic import BaseModel, Field, model_validator
@@ -220,7 +220,7 @@ class CompletionResponseChoice(BaseModel):
prompt_token_ids: Optional[List[int]] = None
completion_token_ids: Optional[List[int]] = None
arrival_time: Optional[float] = None
logprobs: Optional[int] = None
logprobs: Optional[CompletionLogprobs] = None
reasoning_content: Optional[str] = None
finish_reason: Optional[Literal["stop", "length", "tool_calls"]]
tool_calls: Optional[List[DeltaToolCall | ToolCall]] = None
@@ -239,6 +239,17 @@ class CompletionResponse(BaseModel):
usage: UsageInfo
class CompletionLogprobs(BaseModel):
"""
Completion logprobs.
"""
tokens: Optional[List[str]] = None
token_logprobs: Optional[List[float]] = None
top_logprobs: Optional[List[Dict]] = None
text_offset: Optional[List[int]] = None
class CompletionResponseStreamChoice(BaseModel):
"""
Completion response choice for stream response.
@@ -247,9 +258,9 @@ class CompletionResponseStreamChoice(BaseModel):
index: int
text: str
arrival_time: float = None
logprobs: Optional[CompletionLogprobs] = None
prompt_token_ids: Optional[List[int]] = None
completion_token_ids: Optional[List[int]] = None
logprobs: Optional[float] = None
reasoning_content: Optional[str] = None
finish_reason: Optional[Literal["stop", "length", "tool_calls"]] = None
tool_calls: Optional[List[DeltaToolCall | ToolCall]] = None