Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[doc] Update benchmark command in w4a16.md #500

Merged
merged 6 commits into from
Oct 13, 2023
Merged

[doc] Update benchmark command in w4a16.md #500

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
ab3f533
[doc] Update benchmark command in w4a16.md
del-zhenwu Sep 27, 2023
8752b8e
Update w4a16.md
del-zhenwu Sep 27, 2023
dd5b6b3
Update w4a16.md
del-zhenwu Sep 28, 2023
574d1f3
[doc] Update w4a16.md
del-zhenwu Sep 28, 2023
6e1a790
fix lint error
del-zhenwu Oct 11, 2023
18a96ba
[doc] update model_path & prompt_tokens
del-zhenwu Oct 13, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 6 additions & 2 deletions docs/en/w4a16.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -62,10 +62,14 @@ Memory (GB) comparison results between 4-bit and 16-bit model with context size
| Llama-2-7B-chat | 15.1 | 6.3 | 16.2 | 7.5 |
| Llama-2-13B-chat | OOM | 10.3 | OOM | 12.0 |

```
pip install nvidia-ml-py
```

```shell
python benchmark/profile_generation.py \
./workspace \
--concurrency 1 --input_seqlen 1 --output_seqlen 512
--model-path ./workspace \
--concurrency 1 8 --prompt-tokens 1 512 --completion-tokens 2048 512
```

## 4-bit Weight Quantization
Expand Down
8 changes: 6 additions & 2 deletions docs/zh_cn/w4a16.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -60,10 +60,14 @@ python3 -m lmdeploy.serve.turbomind ./workspace --server_name {ip_addr} ----serv
| Llama-2-7B-chat | 15.1 | 6.3 | 16.2 | 7.5 |
| Llama-2-13B-chat | OOM | 10.3 | OOM | 12.0 |

```
pip install nvidia-ml-py
```

```shell
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

可以加下第三方库安装不

pip install nvidia-ml-py

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

好

python benchmark/profile_generation.py \
./workspace \
--concurrency 1 --input_seqlen 1 --output_seqlen 512
--model-path ./workspace \
--concurrency 1 8 --prompt-tokens 1 512 --completion-tokens 2048 512
```

## 4bit 权重量化
Expand Down
Loading