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] Support CudaGraph and optimize flash_attn_unpadded and fused_neox_rope_embedding (#6553)

Browse Source
This commit is contained in:
yzwu
2026-03-02 14:07:17 +08:00
committed by GitHub
parent ecfd088a03
commit 6674131b0b
25 changed files with 723 additions and 123 deletions
Download Patch File Download Diff File Expand all files Collapse all files
custom_ops/setup_ops.py
+4
View File
@@ -563,12 +563,16 @@ elif paddle.is_compiled_with_custom_device("iluvatar_gpu"):
"gpu_ops/update_inputs_v1.cu",
"gpu_ops/get_img_boundaries.cc",
"gpu_ops/set_stop.cu",
"gpu_ops/fused_neox_rope_embedding.cu",
"gpu_ops/get_output_ep.cc",
"iluvatar_ops/moe_dispatch.cu",
"iluvatar_ops/moe_reduce.cu",
"iluvatar_ops/flash_attn_unpadded.cu",
"iluvatar_ops/paged_attn.cu",
"iluvatar_ops/prefill_fused_attn.cu",
"iluvatar_ops/mixed_fused_attn.cu",
"iluvatar_ops/w8a16_group_gemm.cu",
"iluvatar_ops/w8a16_group_gemv.cu",
"iluvatar_ops/runtime/iluvatar_context.cc",
"iluvatar_ops/cpp_extensions.cc",
],