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

[Iluvatar] Optimize decode group_gemm and Support cuda graph for ernie (#6803)

Browse Source
This commit is contained in:
yzwu
2026-03-12 19:21:17 +08:00
committed by GitHub
parent 250ce40b40
commit 901b38c936
9 changed files with 140 additions and 81 deletions
Download Patch File Download Diff File Expand all files Collapse all files
custom_ops/setup_ops.py
+1
View File
@@ -579,6 +579,7 @@ elif paddle.is_compiled_with_custom_device("iluvatar_gpu"):
"iluvatar_ops/mixed_fused_attn.cu",
"iluvatar_ops/w8a16_group_gemm.cu",
"iluvatar_ops/w8a16_group_gemv.cu",
"iluvatar_ops/restore_tokens_per_expert.cu",
"iluvatar_ops/runtime/iluvatar_context.cc",
"iluvatar_ops/cpp_extensions.cc",
],