grouped-nf4-gemm

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

v0.33.4by Jordan AndersonMIT

3.4K

downloads (30d)

AI Health Summary — Claude-generated analysis of download trends, maintenance, and risk signals.

No known vulnerabilities in the latest version

Based on latest version 0.33.4. If you're running an older version, check OSV for your specific version.

Exclude CI/CDPRO

Best Day

620

Sep 4

Worst Day

Sep 22

Peaks On

Fris

191 avg

Quietest

Tues

44 avg

Markdown

[![PyPI Stats](/api/badges/grouped-nf4-gemm?period=month)](/packages/grouped-nf4-gemm)

HTML

<a href="/packages/grouped-nf4-gemm"><img src="/api/badges/grouped-nf4-gemm?period=month" alt="PyPI Stats"></a>