apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-05 08:37:06 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

Revert "[Feature] block sparse attention (#3209)" (#3647)

Browse Source 
This reverts commit 646a0c2fd8.
This commit is contained in:
Jiang-Jia-Jun
2025-08-27 17:35:04 +08:00
committed by GitHub
parent b2afdf4fc6
commit c694fa2879
31 changed files with 10 additions and 6507 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
custom_ops/gpu_ops/cpp_extensions.cc
View File

@@ -784,15 +784,15 @@ void SpeculateStepPaddle(
const int max_draft_tokens);
void MergePrefillDecodeOutput(
const paddle::Tensor &encoder_res,
const paddle::Tensor &decoder_res,
const paddle::Tensor &seq_lens_encoder,
const paddle::Tensor &seq_lens_decoder,
const paddle::Tensor &seq_lens_this_time,
const paddle::Tensor &cu_seq_q,
const int head_num,
const int head_dim,
const int max_token);
const paddle::Tensor &encoder_res,
const paddle::Tensor &decoder_res,
const paddle::Tensor &seq_lens_encoder,
const paddle::Tensor &seq_lens_decoder,
const paddle::Tensor &seq_lens_this_time,
const paddle::Tensor &cu_seq_q,
const int head_num,
const int head_dim,
const int max_token);
std::vector<paddle::Tensor> TopPSamplingReject(const paddle::Tensor &probs,
const paddle::Tensor &top_p,