apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-05 16:48:03 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[Feature 2.0.2] support top_k_top_p sampling (#2789)

Browse Source 
* support top_k_top_p sampling

* fix

* add api param

* add api para

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* change func name
This commit is contained in:
Sunny-bot1
2025-07-10 12:01:51 +08:00
committed by GitHub
parent 1fe37cb7e8
commit 1107e08cd9
18 changed files with 524 additions and 134 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
custom_ops/setup_ops.py
View File

@@ -267,6 +267,7 @@ elif paddle.is_compiled_with_cuda():
"gpu_ops/text_image_index_out.cu",
"gpu_ops/text_image_gather_scatter.cu",
"gpu_ops/sample_kernels/rejection_top_p_sampling.cu",
"gpu_ops/sample_kernels/top_k_renorm_probs.cu",
"gpu_ops/get_position_ids_and_mask_encoder_batch.cu",
"gpu_ops/fused_rotary_position_encoding.cu",
"gpu_ops/noaux_tc.cu",