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

[Graph Optimization] Add full_cuda_graph to control subgraph split (#6027)

Browse Source
This commit is contained in:
Ryan
2026-01-14 11:43:59 +08:00
committed by GitHub
parent 456637002d
commit 0d1a5e70bc
6 changed files with 21 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/ce/deploy/ernie45t_21b_cinn_fp8.yaml
+1
View File
@@ -6,3 +6,4 @@ graph_optimization_config:
graph_opt_level: 2
sot_warmup_sizes: [2,16,32,64]
use_cudagraph: True
full_cuda_graph: False
tests/ce/deploy/ernie45t_21b_cinn_wint4.yaml
+1
View File
@@ -6,3 +6,4 @@ graph_optimization_config:
graph_opt_level: 2
sot_warmup_sizes: [2,16,32,64]
use_cudagraph: True
full_cuda_graph: False
tests/ce/deploy/ernie45t_21b_sot_fp8.yaml
+1
View File
@@ -6,3 +6,4 @@ graph_optimization_config:
graph_opt_level: 1
sot_warmup_sizes: [2,16,32,64]
use_cudagraph: True
full_cuda_graph: False
tests/ce/deploy/ernie45t_21b_sot_wint4.yaml
+1
View File
@@ -6,3 +6,4 @@ graph_optimization_config:
graph_opt_level: 1
sot_warmup_sizes: [2,16,32,64]
use_cudagraph: True
full_cuda_graph: False