apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2026-04-23 08:21:53 +08:00
Code Issues Actions 19 Packages Projects Releases Wiki Activity

[FDConfig]Remove max_model_len in FDConfig (#4350)

Browse Source 
* modify max_model_len

* fix unittest

* fix unittest

---------

Co-authored-by: root <root@yqlcc01-sys-rpm12rzmwjd.yqlcc01.baidu.com>
This commit is contained in:
YuanRisheng
2025-10-11 14:04:17 +08:00
committed by GitHub
parent 365601ea5a
commit a2ec2c4152
36 changed files with 127 additions and 121 deletions
Download Patch File Download Diff File Expand all files Collapse all files
fastdeploy/model_executor/models/qwen2_5_vl/qwen2_5_vl.py
+1 -1
View File
@@ -154,7 +154,7 @@ class Qwen2_5_VLForConditionalGeneration(ModelForCasualLM):
# Persistent buffers for CUDA graphs.
self._input_embeddings = paddle.zeros(
[fd_config.parallel_config.max_model_len, fd_config.model_config.hidden_size],
[fd_config.model_config.max_model_len, fd_config.model_config.hidden_size],
dtype=fd_config.model_config.dtype,
)