experts4bit-qlora
Train and serve MoE models that do not fit in VRAM: fused 4-bit experts, QLoRA, CPU/NVMe offload, and fast inference on consumer NVIDIA GPUs.
View on Github
Activity
- Latest release
- 1w ago
- Total releases
- 62
- Cadence
- ~daily
- Last 12 months
- 62
Reach
- Stars
- 3
Details
- License
- MIT
- First release
- Jul 01, 2026
Releases
| Version | Released | |
|---|---|---|
0.35.3
patch
| ||
0.35.2
patch
| ||
0.35.1
patch
| ||
0.35.0
minor
| ||
0.34.0
minor
| ||
0.33.0
minor
| ||
0.32.0
minor
| ||
0.31.2
patch
| ||
0.31.1
patch
| ||
0.31.0
minor
| ||
0.30.0
minor
| ||
0.29.0
minor
| ||
0.28.0
minor
| ||
0.27.0
minor
| ||
0.26.0
minor
| ||
0.25.0
minor
| ||
0.24.2
patch
| ||
0.24.1
patch
| ||
0.24.0
minor
| ||
0.23.0
minor
| ||
0.22.0
minor
| ||
0.21.0
minor
| ||
0.20.0
minor
| ||
0.19.1
patch
| ||
0.19.0
minor
| ||
0.18.0
minor
| ||
0.17.5
patch
| ||
0.17.4
patch
| ||
0.17.3
patch
| ||
0.17.2
patch
| ||
0.17.1
patch
| ||
0.17.0
minor
| ||
0.16.3
patch
| ||
0.16.2
patch
| ||
0.16.1
patch
| ||
0.16.0
minor
| ||
0.15.0
minor
| ||
0.14.0
minor
| ||
0.13.0
minor
| ||
0.12.0
minor
| ||
0.11.1
patch
| ||
0.11.0
minor
| ||
0.10.0
minor
| ||
0.9.1
patch
| ||
0.9.0
minor
| ||
0.8.0
minor
| ||
0.7.1
patch
| ||
0.7.0
minor
| ||
0.6.7
patch
| ||
0.6.6
patch
|
1–50 of 62