apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2026-04-23 00:17:25 +08:00
Code Issues Actions 19 Packages Projects Releases Wiki Activity

[Models] Add Qwen3-VL Model Support (#5763)

Browse Source 
* support v1 loader

* remove useless code

* remove useless

* [Model] support Qwen3VL images success

* [Model] support Qwen3VL rope_3d

* [Model] support Qwen3VL remove log

* [Model] support Qwen3VL RL

* [Model] support Qwen3VL tp

* [Model] support Qwen3VL video

* [Model] support Qwen3VL fix ernievl

* [Model] support Qwen3VL fix get_image_boundaries.cc array out of bounds

* [Model] support Qwen3VL fix multi card

* [Model] support Qwen3VL file close

* [Model] support Qwen3VL fix ce

* [Model] support Qwen3VL fix unittest

* [Model] support Qwen3VL add unittest

---------

Co-authored-by: Ayakouji <yuhongh@qq.com>
This commit is contained in:
CSWYF3634076
2025-12-29 17:39:33 +08:00
committed by GitHub
parent a3f0696e35
commit 9286403570
36 changed files with 5917 additions and 91 deletions
Download Patch File Download Diff File Expand all files Collapse all files
fastdeploy/worker/metax_model_runner.py
+1
View File
@@ -2865,6 +2865,7 @@ class MetaxModelRunner(ModelRunnerBase):
base=self.model_config.rope_theta,
max_position=self.model_config.max_model_len,
freq_allocation=getattr(self.model_config, "freq_allocation", 20),
rope_scaling=getattr(self.model_config, "rope_scaling", {}),
model_type=self.model_config.model_type,
max_len_lst=max_len_lst,
cumsum_seqlens=cumsum_seqlens,