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/pre_and_post_process.py
View File

@@ -106,7 +106,7 @@ def pre_process(
"""
# Remove padding
max_len = input_ids.shape[1]
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)
output_padding_offset = None
output_cum_offsets = None
@@ -132,7 +132,7 @@ def pre_process(
if isinstance(seq_lens_output, list):
seq_lens_output = seq_lens_output[0]
output_token_num = paddle.sum(seq_lens_output)
output_cum_offsets_tmp = paddle.cumsum(max_len - seq_lens_output)
output_cum_offsets_tmp = paddle.cumsum(max_len - seq_lens_output, dtype="int32")
output_padding_offset, output_cum_offsets = speculate_get_output_padding_offset(
output_cum_offsets_tmp,
output_token_num,