apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-04 16:22:57 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[vl] Use top_k from config.json (#2831)
Some checks failed
Deploy GitHub Pages / deploy (push) Has been cancelled
Details

Browse Source
This commit is contained in:
bukejiyu
2025-07-15 00:39:12 +08:00
committed by GitHub
parent 7cdd8d290d
commit 15c8c240b5
1 changed files with 0 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
fastdeploy/worker/vl_gpu_model_runner.py
View File

@@ -235,8 +235,6 @@ class GPUVLModelRunner(VLModelRunnerBase):
fd_config.model_config.think_end_id = tokenizer.get_vocab()["</think>"]
fd_config.model_config.max_text_id = fd_config.model_config.im_patch_id
fd_config.model_config.sequence_parallel = False
# TODO(YuanRisheng) The moe_k in develop is fixed to 8, need to be changed according to json config
fd_config.model_config.moe_k = 8
self.fd_config = fd_config
self.model_cfg = self.fd_config.model_config
self.image_preprocess = self._init_image_preprocess(