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

add glm benchmark yaml (#4289)

Browse Source
This commit is contained in:
tianlef
2025-09-26 14:23:29 +08:00
committed by GitHub
parent 67e693b18b
commit 8a964329f4
3 changed files with 19 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
benchmarks/yaml/GLM45-air-32k-bf16.yaml Normal file
View File

@@ -0,0 +1,5 @@
max_model_len: 32768
max_num_seqs: 128
tensor_parallel_size: 4
use_cudagraph: True
load_choices: "default_v1"

6
benchmarks/yaml/GLM45-air-32k-wfp8afp8.yaml Normal file
View File

@@ -0,0 +1,6 @@
max_model_len: 32768
max_num_seqs: 128
tensor_parallel_size: 4
use_cudagraph: True
load_choices: "default_v1"
quantization: wfp8afp8

8
benchmarks/yaml/request_yaml/GLM-32k.yaml Normal file
View File

@@ -0,0 +1,8 @@
top_p: 0.95
temperature: 0.6
metadata:
min_tokens: 1
max_tokens: 12288
repetition_penalty: 1.0
frequency_penalty: 0
presence_penalty: 0