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 return logprob of generated tokens (#2784)

Browse Source 
* online chat support logprobs

* check xpu

* check vl_gpu_model_runner

* only cuda support logprob

* get_worker() check platform

---------

Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
This commit is contained in:
chen
2025-07-10 15:47:42 +08:00
committed by GitHub
parent 39d2a1de46
commit 823a47e64a
21 changed files with 592 additions and 105 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
fastdeploy/input/ernie_processor.py
View File

@@ -20,10 +20,9 @@ import numpy as np
from paddleformers.generation import GenerationConfig
from fastdeploy import envs
from fastdeploy.utils import data_processor_logger
from fastdeploy.input.ernie_tokenizer import ErnieBotTokenizer
from fastdeploy.input.text_processor import BaseDataProcessor
from fastdeploy.utils import data_processor_logger
_SAMPLING_EPS = 1e-5
@@ -444,3 +443,7 @@ class ErnieProcessor(BaseDataProcessor):
data_processor_logger.debug(
f"processed stop_seqs: {stop_seqs}, {stop_seqs_len}")
return stop_seqs, stop_seqs_len
def process_logprob_response(self, token_ids, **kwargs):
full_text = self.tokenizer.decode(token_ids, **kwargs)
return full_text