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

[Metax] adapt DeepSeek (#4498)

Browse Source
This commit is contained in:
xiaozude
2025-10-24 10:14:53 +08:00
committed by GitHub
parent 8718fa34b2
commit f7069b8057
19 changed files with 1538 additions and 324 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
fastdeploy/config.py
View File

@@ -1144,7 +1144,7 @@ class CacheConfig:
self.kv_cache_ratio = 1.0
else:
self.kv_cache_ratio = 0.75
self.enc_dec_block_num = 0 if current_platform.is_maca() else envs.FD_ENC_DEC_BLOCK_NUM
self.enc_dec_block_num = envs.FD_ENC_DEC_BLOCK_NUM
self.prealloc_dec_block_slot_num_threshold = 12
self.cache_dtype = "bfloat16"
self.model_cfg = None