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

[Model] tp+ep support v1_loader (#5465)

Browse Source 
* [Model] tp+ep support v1_loader

* fix

* fix mtp_linear

* fix mtp_linear

* fix

* fix

* fix v0 loader

* fix

* Add get_tensor for ep

* fix linear weight_loader

* fix typo

* fix
This commit is contained in:
Longzhi Wang
2025-12-18 14:31:54 +08:00
committed by GitHub
parent c89a62e550
commit d8587e987e
8 changed files with 48 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
fastdeploy/model_executor/layers/quantization/block_wise_fp8.py
View File

@@ -138,7 +138,9 @@ class BlockWiseFP8LinearMethod(QuantMethodBase):
weight_shape = layer.weight_shape
weight_scale_inv_shape = weight_scale_inv_shape
extra_weight_attrs["output_dim"] = (
not extra_weight_attrs["output_dim"] if extra_weight_attrs["output_dim"] is not None else None
not extra_weight_attrs["output_dim"]
if extra_weight_attrs.get("output_dim", None) is not None
else None
)
layer.weight_dtype = "float8_e4m3fn"