apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2026-04-23 00:17:25 +08:00
Code Issues Actions 19 Packages Projects Releases Wiki Activity

[Model Runner] Refactor execute_model for GPU async scheduling (#6176)

Browse Source
This commit is contained in:
sunxin
2026-01-28 14:19:33 +08:00
committed by GitHub
parent ce06c6dfb3
commit 27f8799f04
9 changed files with 188 additions and 62 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/operators/test_update_inputs_v1.py
+1 -1
View File
@@ -156,7 +156,7 @@ class TestUpdateInputsV1(unittest.TestCase):
is_block_step = np.random.randint(0, 2, [max_bs]).astype("bool")
stop_flags = paddle.to_tensor(stop_flags)
not_need_stop = paddle.to_tensor(not_need_stop, place=paddle.CPUPlace())
not_need_stop = paddle.to_tensor(not_need_stop)
seq_lens_this_time = paddle.to_tensor(seq_lens_this_time)
seq_lens_encoder = paddle.to_tensor(seq_lens_encoder)
seq_lens_decoder = paddle.to_tensor(seq_lens_decoder)