apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-06 09:07:10 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[BugFix] fix prompt token ids type (#2994)

Browse Source 
* Update serving_completion.py

* fix

* fix
This commit is contained in:
ltd0924
2025-07-23 21:00:56 +08:00
committed by GitHub
parent 5d1788c7b5
commit fb0f284e67
2 changed files with 8 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
fastdeploy/entrypoints/openai/serving_chat.py
View File

@@ -20,7 +20,7 @@ import time
import traceback
import uuid
from typing import List, Optional
import numpy as np
import msgpack
import aiozmq
from aiozmq import zmq
@@ -75,6 +75,8 @@ class OpenAIServingChat:
current_req_dict = request.to_dict_for_infer(request_id)
current_req_dict["arrival_time"] = time.time()
prompt_token_ids = self.engine_client.format_and_add_data(current_req_dict)
if isinstance(prompt_token_ids, np.ndarray):
prompt_token_ids = prompt_token_ids.tolist()
except Exception as e:
return ErrorResponse(code=400, message=str(e))

8
fastdeploy/entrypoints/openai/serving_completion.py
View File

@@ -18,6 +18,7 @@ import asyncio
import aiozmq
import json
import msgpack
import numpy as np
from aiozmq import zmq
from asyncio import FIRST_COMPLETED, AbstractEventLoop, Task
import time
@@ -105,9 +106,10 @@ class OpenAIServingCompletion:
current_req_dict = request.to_dict_for_infer(request_id_idx, prompt)
try:
current_req_dict["arrival_time"] = time.time()
prompt_batched_token_ids.append(
self.engine_client.format_and_add_data(current_req_dict)
)
prompt_token_ids = self.engine_client.format_and_add_data(current_req_dict)
if isinstance(prompt_token_ids, np.ndarray):
prompt_token_ids = prompt_token_ids.tolist()
prompt_batched_token_ids.append(prompt_token_ids)
except Exception as e:
return ErrorResponse(message=str(e), code=400)