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

[Metax] optimize cutlass moe and flash attention backend (#5128)

Browse Source
This commit is contained in:
Neil Zhu
2025-11-20 16:12:35 +08:00
committed by GitHub
parent f1e36ff2f7
commit 0edda75a56
5 changed files with 469 additions and 161 deletions
Download Patch File Download Diff File Expand all files Collapse all files
custom_ops/setup_ops.py
+1
View File
@@ -629,6 +629,7 @@ elif paddle.device.is_compiled_with_custom_device("metax_gpu"):
"metax_ops/moe_ffn.cu",
"metax_ops/moe_reduce.cu",
"metax_ops/fused_moe.cu",
"metax_ops/apply_rope.cu",
]
sources += find_end_files("gpu_ops/speculate_decoding", ".cu")