apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-12-24 13:28:13 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[Iluvatar] Support V1_KVCACHE_SCHEDULER and paddleocr-vl rope mode (#5555)

Browse Source
This commit is contained in:
yzwu
2025-12-18 18:14:25 +08:00
committed by GitHub
parent 48f3e9797e
commit ac013803f3
24 changed files with 1212 additions and 1090 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
custom_ops/setup_ops.py
View File

@@ -555,6 +555,9 @@ elif paddle.is_compiled_with_custom_device("iluvatar_gpu"):
"gpu_ops/set_data_ipc.cu",
"gpu_ops/limit_thinking_content_length_v1.cu",
"gpu_ops/limit_thinking_content_length_v2.cu",
"gpu_ops/recover_decode_task.cu",
"gpu_ops/update_inputs_v1.cu",
"gpu_ops/get_img_boundaries.cc",
"iluvatar_ops/moe_dispatch.cu",
"iluvatar_ops/moe_reduce.cu",
"iluvatar_ops/paged_attn.cu",