mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2026-04-23 00:17:25 +08:00
[Graph Optimization][BugFix][CI] Fix 0size bug && add unitest (#5495)
This commit is contained in:
@@ -0,0 +1,8 @@
|
||||
max_model_len: 32768
|
||||
max_num_seqs: 128
|
||||
tensor_parallel_size: 1
|
||||
quantization: wint4
|
||||
graph_optimization_config:
|
||||
graph_opt_level: 2
|
||||
sot_warmup_sizes: [2,16,32,64]
|
||||
use_cudagraph: True
|
||||
Reference in New Issue
Block a user