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

[Optimization] Support FA2/FA3/FA4 with attn_mask_q (#6354)

Browse Source 
* support FA4 sm100

* flash attn backend support mask

* flash attn backend run flashmask correct

* add test for flash_attn_backend and flash_attn_func

* check

* add test for fa4

* requirements.txt add fa4 whl

* check test on sm100

* fix CI conflict

* add enable_torch_proxy for flash_mask

* lazy import fa4

* check

* fix tests import

* check test_load_mpt import
This commit is contained in:
chen
2026-02-05 14:39:00 +08:00
committed by GitHub
parent 72edd394d9
commit 29a313a402
22 changed files with 999 additions and 101 deletions
Download Patch File Download Diff File Expand all files Collapse all files
custom_ops/setup_ops.py
+1
View File
@@ -313,6 +313,7 @@ elif paddle.is_compiled_with_cuda():
"gpu_ops/fused_neox_rope_embedding.cu",
"gpu_ops/gelu_tanh.cu",
"gpu_ops/reasoning_phase_token_constraint.cu",
"gpu_ops/get_attn_mask_q.cu",
]
# pd_disaggregation