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

Update vllm.md #77

Merged
merged 1 commit into from
Sep 9, 2024
Merged

Update vllm.md #77

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
6 changes: 3 additions & 3 deletions docs/zh_cn/source/backend/vllm.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -85,7 +85,7 @@ quant:
请注意，在此步骤中需要将 `pack_mode` 参数设置为 `vllm_pack`, 这会将4-bit的权重`打包`为`torch.int32`的格式存储，供VLLM直接加载推理。


此外，如果 AWQ 无法满足精度需求，我们建议使用 [章节](https://llmc-zhcn.readthedocs.io/zh_cn/practice/awq_omni.md)介绍的 **AWQ+OmniQuant 组合算法** 来进一步提升精度。在此也给出相应的[配置文件](https://github.com/ModelTC/llmc/tree/main/configs/quantization/backend/vllm/w4a16_combin)
此外，如果 AWQ 无法满足精度需求，我们建议使用 [章节](https://llmc-zhcn.readthedocs.io/en/latest/practice/awq_omni.html)介绍的 **AWQ+OmniQuant 组合算法** 来进一步提升精度。在此也给出相应的[配置文件](https://github.com/ModelTC/llmc/tree/main/configs/quantization/backend/vllm/w4a16_combin)


**W8A8**
Expand Down Expand Up @@ -116,7 +116,7 @@ quant:
quant_out: True
```

此外，如果 AWQ 无法满足精度需求，我们建议使用 [章节](https://llmc-zhcn.readthedocs.io/zh_cn/practice/quarot_gptq.md) 介绍的 **Quarot+GPTQ 组合算法** 来进一步提升精度。在此也给出相应的[配置文件](https://github.com/ModelTC/llmc/tree/main/configs/quantization/backend/vllm/w8a8_combin)
此外，如果 AWQ 无法满足精度需求，我们建议使用 [章节](https://llmc-zhcn.readthedocs.io/en/latest/practice/quarot_gptq.html) 介绍的 **Quarot+GPTQ 组合算法** 来进一步提升精度。在此也给出相应的[配置文件](https://github.com/ModelTC/llmc/tree/main/configs/quantization/backend/vllm/w8a8_combin)


### 1.3.3 真实量化模型导出
Expand Down Expand Up @@ -180,4 +180,4 @@ curl http://localhost:8000/v1/completions \
"max_tokens": 128,
"temperature": 0
}'
```
```
Loading