vllm-project / vllm-project/aibrix
The best practices for multi-node multi-GPU deployment of DeepSeek-R1-671B
Open
kind/support
triage/accepted
- Dominant language
- Go
- Stars
- 5.1k
- Forks
- 694
- Avg merge
- 1d 19h
- Merged PRs (30d)
- 98
Description
### 🚀 Feature Description and Motivation
Is there a detailed tutorial for multi-node multi-GPU deployment of DeepSeek-R1-671B?
### Use Case
deployment of DeepSeek-R1-671B
### Proposed Solution
_No response_
Contributor guide
Assessment
This issue has not been assessed yet.