biggy/DeepSeek-R1
1
0
Fork 0
mirror of https://github.com/deepseek-ai/DeepSeek-R1.git synced 2025-04-29 02:19:22 +00:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

Compare commits

base: biggy:e62e6f9ac4b2d48dd68f63a54c1c5564115cb0da
Branches Tags
biggy:main
...
compare: biggy:1f6970967da4c1f084dc268e76a352be212255dd
Branches Tags
biggy:main

2 Commits
e62e6f9ac4 ... 1f6970967d

Author SHA1 Message Date
Didier Durand
1f6970967d
Merge a55ff348c988f3c6d3c5646297fb07a164569bb8 into 45b89c6cb13cf6b01da05ef9a7379f13f8d3baf2 2025-02-18 22:57:22 +07:00
Didier Durand
a55ff348c9
Update README.md: --tp invalid is launch option 
Hi,
As  https://github.com/sgl-project/sglang/blob/main/python/sglang/srt/server_args.py at line 497 and next, --tp is not a valid command option.

Possible values --tensor-parallel-size or --tp-size

I chose --tensor-parallel-size to remain consistent with previous command suggested by this README
 2025-02-08 08:38:03 +01:00
1 changed files with 1 additions and 1 deletions
Show Stats Expand all files Collapse all files

2
README.md
View File

@ -180,7 +180,7 @@ vllm serve deepseek-ai/DeepSeek-R1-Distill-Qwen-32B --tensor-parallel-size 2 --m
You can also easily start a service using [SGLang](https://github.com/sgl-project/sglang)
```bash
python3 -m sglang.launch_server --model deepseek-ai/DeepSeek-R1-Distill-Qwen-32B --trust-remote-code --tp 2
python3 -m sglang.launch_server --model deepseek-ai/DeepSeek-R1-Distill-Qwen-32B --trust-remote-code --tensor-parallel-size 2
```
### Usage Recommendations