apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-12-24 13:28:13 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[Feature] support stop_token_ids (#5399)

Browse Source 
* support stop_token_ids

* fix

* delete chinese

* support both

* delete print
This commit is contained in:
lizexu123
2025-12-09 17:49:12 +08:00
committed by GitHub
parent df67379bc3
commit 95eab9f9ee
18 changed files with 377 additions and 127 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
fastdeploy/input/qwen_vl_processor/qwen_vl_processor.py
View File

@@ -18,6 +18,7 @@ import numpy as np
from fastdeploy.engine.request import Request
from fastdeploy.input.text_processor import DataProcessor as TextProcessor
from fastdeploy.input.utils import process_stop_token_ids
from fastdeploy.utils import data_processor_logger
from .process import DataProcessor
@@ -209,11 +210,8 @@ class QwenVLProcessor(TextProcessor):
if not request.get("eos_token_ids"):
request["eos_token_ids"] = self.eos_token_ids
stop_sequences = request.get("stop", [])
if stop_sequences:
stop_seqs, stop_seqs_len = self.update_stop_seq(stop_sequences)
request["stop_token_ids"] = stop_seqs
request["stop_seqs_len"] = stop_seqs_len
# processing stop_sequences and stop_token_ids
process_stop_token_ids(request, self.update_stop_seq)
bad_words = request.get("bad_words")
bad_words_token_ids = request.get("bad_words_token_ids")