improvements to MoE perf (Deepseek V3)
Open
Performance
- Dominant language
- Python
- Stars
- 2k
- Forks
- 561
- Avg merge
- 4d 5h
- Merged PRs (30d)
- 145
Description
Tracking v0.5 items for MoE performance, example model is deepseek v3.
Contributor guide
Assessment
This issue has not been assessed yet.