amf-fast-inference
uses pruning and quatisation to make inference speed faster
Activity
- Latest release
- 2y ago
- Total releases
- 3
- Cadence
- ~24 days
- Last 12 months
- 0
Details
- License
- MIT
- First release
- Apr 04, 2024
Releases
| Version | Released | |
|---|---|---|
0.0.3
patch
| ||
0.0.2
patch
| ||
0.0.1
initial
|