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

[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

1
tests/graph_optimization/test_cuda_graph_spec_decode.py
View File

@@ -106,6 +106,7 @@ class TestCUDAGrpahSpecDecode(unittest.TestCase):
cache_config = CacheConfig({})
parallel_config = ParallelConfig(args={})
model_config = Mock()
model_config.max_model_len = 512
# Initialize cuda graph capture list
graph_opt_config._set_cudagraph_sizes(max_num_seqs=scheduler_config.max_num_seqs)
graph_opt_config.init_with_cudagrpah_size(max_capture_size=scheduler_config.max_num_seqs)