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

[BugFix] fix dynamic c8 in v1 loader (#5562)

Browse Source
This commit is contained in:
Yuanle Liu
2025-12-15 20:07:54 +08:00
committed by GitHub
parent 532f9ba227
commit b8e4828373
1 changed files with 5 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
fastdeploy/model_executor/layers/quantization/kv_cache.py
+5 -4
View File
@@ -263,10 +263,11 @@ class KVCacheMethodBase(QuantMethodBase):
"""
use for loader v1
"""
if layer.cache_k_scale._is_initialized():
layer.cache_k_out_scale.set_value(1 / layer.cache_k_scale)
if layer.cache_v_scale._is_initialized():
layer.cache_v_out_scale.set_value(1 / layer.cache_v_scale)
if "block_wise" not in layer.cache_quant_type_str:
if layer.cache_k_scale._is_initialized():
layer.cache_k_out_scale.set_value(1 / layer.cache_k_scale)
if layer.cache_v_scale._is_initialized():
layer.cache_v_out_scale.set_value(1 / layer.cache_v_scale)
def apply(self, layer):
"""