apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2026-04-23 08:21:53 +08:00
Code Issues Actions 19 Packages Projects Releases Wiki Activity

[SOT][Cudagraph] Remove BreakGraph of #3302 && update CustomOp (#3694)

Browse Source 
* rm inplace info && to(gpu)

* update append_attention

* unpin paddle version

* add full_cuda_graph=False

* add blank line

---------

Co-authored-by: SigureMo <sigure.qaq@gmail.com>
This commit is contained in:
Ryan
2025-10-17 10:57:55 +08:00
committed by GitHub
parent a37c9416ac
commit 49cea8fb1c
5 changed files with 12 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files
fastdeploy/model_executor/layers/attention/ops/append_attention.py
+1 -1
View File
@@ -205,7 +205,7 @@ def append_attention_with_output(
append_attention
"""
if current_platform.is_cuda():
append_attention_with_output_gpu(
return append_attention_with_output_gpu(
qkv,
key_cache,
value_cache,