apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-11-01 12:22:53 +08:00
Code Issues Actions 6 Packages Projects Releases Wiki Activity

[Doc]fix deepseek ce (#4560)

Browse Source
This commit is contained in:
tianlef
2025-10-23 14:09:11 +08:00
committed by GitHub
parent bbf06b9ff7
commit 2676a918f0
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
benchmarks/yaml/deepseek-32k-tp8-wint4.yaml
View File

@@ -3,7 +3,7 @@ load_choices: "default_v1"
graph_optimization_config:
use_cudagraph: True
use_unique_memory_pool: True
no_enable_prefix_caching: True
enable_prefix_caching: False
max_num_seqs: 256
max_model_len: 32768
tensor_parallel_size: 8