apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-12-24 13:28:13 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

remove seq_lens_this_time (#4821)

Browse Source
This commit is contained in:
周周周
2025-11-06 11:06:28 +08:00
committed by GitHub
parent 62dfad4a5f
commit 69fa741763
2 changed files with 4 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
fastdeploy/worker/gpu_model_runner.py
View File

@@ -2050,7 +2050,7 @@ class GPUModelRunner(ModelRunnerBase):
self,
model_forward_batch: Optional[List[Request]] = None,
num_running_requests: int = None,
) -> Optional[ModelRunnerOutput]:
) -> None:
"""
The Entrance of model execute.
Args:
@@ -2140,10 +2140,6 @@ class GPUModelRunner(ModelRunnerBase):
async_output_queue=self.async_output_queue,
)
self.seq_lens_this_time_buffer[:num_running_requests].copy_(
self.share_inputs["seq_lens_this_time"][:num_running_requests], False
)
return None
else:
hidden_states = rebuild_padding(
@@ -2305,9 +2301,6 @@ class GPUModelRunner(ModelRunnerBase):
self.speculative_config.num_speculative_tokens,
)
self.seq_lens_this_time_buffer[:num_running_requests].copy_(
self.share_inputs["seq_lens_this_time"][:num_running_requests], False
)
return None
def _pool(self, hidden_states: paddle.Tensor, num_running_requests: int) -> Optional[ModelRunnerOutput]: