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

[Doc]add text/vl cinn ce config (#5532)

Browse Source
This commit is contained in:
tianlef
2025-12-12 16:16:06 +08:00
committed by GitHub
parent 12c76f8137
commit 13cc7dacfd
2 changed files with 20 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
benchmarks/yaml/eb45-32k-wint4-a800-tp4-cinn.yaml Normal file
View File

@@ -0,0 +1,9 @@
max_model_len: 32768
max_num_seqs: 96
gpu_memory_utilization: 0.85
kv_cache_ratio: 0.71
tensor_parallel_size: 4
quantization: wint4
graph_optimization_config:
use_cudagraph: True
graph_opt_level: 2

11
benchmarks/yaml/eb45-vl-32k-wint4-a800-tp8-cinn.yaml Normal file
View File

@@ -0,0 +1,11 @@
max_model_len: 32768
max_num_seqs: 56
gpu_memory_utilization: 0.9
kv_cache_ratio: 0.8
tensor_parallel_size: 8
quantization: wint4
limit_mm_per_prompt: '{"image": 100, "video": 100}'
reasoning_parser: ernie-45-vl
graph_optimization_config:
use_cudagraph: True
graph_opt_level: 2