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

success run ngram

Browse Source
This commit is contained in:
gongshaotian
2025-08-20 16:27:29 +08:00
parent 9ff2dfb162
commit 8351e83993
27 changed files with 94 additions and 1331 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
fastdeploy/model_executor/graph_optimization/graph_optimization_backend.py
View File

@@ -115,7 +115,7 @@ class GraphOptBackend:
self.runnable = runnable
self.fd_config = fd_config
self.max_captre_batch = fd_config.graph_opt_config.cudagraph_capture_sizes[0]
self.max_captre_size = fd_config.graph_opt_config.cudagraph_capture_sizes[0]
if self.fd_config.graph_opt_config.graph_opt_level > 0:
# 1. Prepare cuda grpah input buffers (contain output of subgraphs)
@@ -138,9 +138,11 @@ class GraphOptBackend:
)
assert kwargs["forward_meta"].ids_remove_padding is not None
batch_size = kwargs["forward_meta"].ids_remove_padding.shape[0]
real_shape = kwargs["forward_meta"].ids_remove_padding.shape[0]
print(f"[GraphOptBackend] real_shape :{real_shape}")
if (not kwargs["forward_meta"].step_use_cudagraph) or (batch_size > self.max_captre_batch):
if (not kwargs["forward_meta"].step_use_cudagraph) or (real_shape > self.max_captre_size):
print("[GraphOptBackend] run dynamic graph")
return self.runnable(**kwargs)
else:
return self.cudagraph_piecewise_backend.__call__(**kwargs)