antirez / antirez/ds4

Performance of DeepSeek V4 Flash on H200 - 70 tokens/s

Open
#564 2 comments 0 reactions 0 assignees View on GitHub
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

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.