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

[Loader] support dummy load weight (#6169)

Browse Source 
* [Loader] support dummy load weight

* [Loader] support dummy load weight v2

* [Loader] support dummy load weight unittest

* [Loader] support dummy load weight unittest v2

* [Loader] support dummy load weight v3 docs and fp8
This commit is contained in:
CSWYF3634076
2026-01-26 13:58:53 +08:00
committed by GitHub
parent adc69c15d0
commit 08c411518f
8 changed files with 273 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
fastdeploy/model_executor/layers/quantization/wfp8afp8.py
+1 -1
View File
@@ -137,7 +137,7 @@ class WFP8AFP8LinearMethod(QuantMethodBase):
layer.weight_dtype = "float8_e4m3fn"
# TODO(YuanRisheng): set weight logic should be moved to process_loaded_weights func
self.skip_quant = False
layer.create_parameter(
layer.weight = layer.create_parameter(
shape=layer.weight_shape,
dtype=layer.weight_dtype,
is_bias=False,