Sign in Sign up
pypi

grouped-nf4-gemm

Triton kernels for 4-bit MoE inference: grouped NF4/MXFP4 GEMM, INT4 GEMV, FP8 paged attention, and CPU/NVMe expert streaming.

Activity

Latest release
1w ago
Total releases
47
Cadence
~daily
Last 12 months
47

Reach

Stars
2

Details

License
MIT
First release
Jul 18, 2026
Releases
Version Released
0.30.2 patch
0.30.1 patch
0.30.0 minor
0.29.0 minor
0.28.0 minor
0.27.0 minor
0.26.0 minor
0.25.0 minor
0.24.0 minor
0.23.0 minor
0.22.0 minor
0.21.0 minor
0.20.0 minor
0.19.0 minor
0.18.0 minor
0.17.0 minor
0.16.0 minor
0.15.1 patch
0.15.0 minor
0.14.0 minor
0.13.2 patch
0.13.1 patch
0.13.0 minor
0.12.0 minor
0.11.0 minor
0.10.0 minor
0.9.0 minor
0.8.3 patch
0.8.2 patch
0.8.1 patch
0.8.0 minor
0.7.1 patch
0.7.0 minor
0.6.0 minor
0.5.1 patch
0.5.0 minor
0.4.0 minor
0.3.1 patch
0.3.0 minor
0.2.6 patch
0.2.5 patch
0.2.4 patch
0.2.2 patch
0.2.1 patch
0.2.0 minor
0.1.1 patch
0.1.0 initial