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 flash attention backend (#5876)

Browse Source
This commit is contained in:
Neil Zhu
2026-01-06 09:52:09 +08:00
committed by GitHub
parent ab553b3b8b
commit 272a371635
6 changed files with 990 additions and 618 deletions
Download Patch File Download Diff File Expand all files Collapse all files
custom_ops/setup_ops.py
+1 -1
View File
@@ -645,9 +645,9 @@ 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_qkv.cu",
"metax_ops/cache_kv_with_rope.cu",
"metax_ops/cpp_extensions.cc",
"metax_ops/split_merge_qkv.cu",
]
sources += find_end_files("gpu_ops/speculate_decoding", ".cu")