mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-10-06 00:57:33 +08:00
[Feature] support top_k_top_p sampling (#2753)
* support top_k_top_p sampling * fix * add api param * add api para * fix * fix * fix * fix * fix * fix * fix
This commit is contained in:
@@ -282,6 +282,7 @@ 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",
|
||||
|
Reference in New Issue
Block a user