Performance of DeepSeek V4 Flash on H200 - 70 tokens/s
Open
- Dominant language
- C
- Stars
- 22.3k
- Forks
- 2.1k
- Avg merge
- 1d 3h
- Merged PRs (30d)
- 4
Description
I do have a H200 at home, and I would love to help get the card to perform better than the current speed. I do believe some code changes are required. Is anyone interested on having this card to work on the model but me? Someone to help me out?
Contributor guide
Assessment
This issue has not been assessed yet.