Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
laibao
llava_vllm
Commits
68e9352f
Commit
68e9352f
authored
Oct 16, 2024
by
laibao
Browse files
No commit message
No commit message
parent
721cbee2
Changes
2
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
15 additions
and
2 deletions
+15
-2
README.md
README.md
+15
-2
doc/images.png
doc/images.png
+0
-0
No files found.
README.md
View file @
68e9352f
...
@@ -101,9 +101,22 @@ python examples/llava_example.py
...
@@ -101,9 +101,22 @@ python examples/llava_example.py
*
**去除了AWS CLI 下载逻辑**
:
*
**去除了AWS CLI 下载逻辑**
:
*
**移除对 `subprocess` 和 `os` 模块的部分依赖**
*
**移除对 `subprocess` 和 `os` 模块的部分依赖**
### 离线批量推理性能测试
### result
使用的加速卡:单卡K100_AI 模型:
[
llava-v1.5-7b
](
http://113.200.138.88:18080/aimodels/llava-v1.5-7b
)
输入:
images:
<div
align=
"center"
>
<img
src=
"./doc/images.png"
width=
"300"
height=
"200"
/>
</div>
1、指定输入输出
```
bash
```
bash
python benchmarks/benchmark_throughput.py
--num-prompts
1
--input-len
32
--output-len
128
--model
Qwen/Qwen1.5-7B-Chat
-tp
1
--trust-remote-code
--enforce-eager
--dtype
float16
python benchmarks/benchmark_throughput.py
--num-prompts
1
--input-len
32
--output-len
128
--model
Qwen/Qwen1.5-7B-Chat
-tp
1
--trust-remote-code
--enforce-eager
--dtype
float16
...
...
doc/images.png
0 → 100644
View file @
68e9352f
625 KB
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment