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

add dtype int32 (#3692)
Some checks failed
CE Compile Job / ce_job_pre_check (push) Has been cancelled
Details
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
Details
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
Details
CE Compile Job / Show Code Archive Output (push) Has been cancelled
Details
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
Details
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
Details
CE Compile Job / CE_UPLOAD (push) Has been cancelled
Details
Deploy GitHub Pages / deploy (push) Has been cancelled
Details

Browse Source
This commit is contained in:
Ryan
2025-08-29 14:56:35 +08:00
committed by GitHub
parent 1bf4fc7f36
commit 45f81b34f0
7 changed files with 9 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
fastdeploy/model_executor/layers/utils.py
View File

@@ -257,7 +257,7 @@ def remove_padding(
- The key sequence lengths (paddle.Tensor).
"""
if current_platform.is_cuda():
cum_offsets_now = paddle.cumsum(max_len - seq_lens_this_time)
cum_offsets_now = paddle.cumsum(max_len - seq_lens_this_time, dtype="int32")
token_num = paddle.sum(seq_lens_this_time)
(
ids_remove_padding,
@@ -301,7 +301,7 @@ def speculate_remove_padding(
- Key sequence lengths (paddle.Tensor).
"""
if current_platform.is_cuda():
cum_offsets_now = paddle.cumsum(max_len - seq_lens_this_time)
cum_offsets_now = paddle.cumsum(max_len - seq_lens_this_time, dtype="int32")
token_num = paddle.sum(seq_lens_this_time)
(
ids_remove_padding,