RepoAlerts
SponsorGet alerts

astding/mmaemu

Library

Get alerts like thisView on GitHubWebsiteShare on X

Can I trust it?

No red flags in our checks.

  • Stars from real accounts No data

    We haven't checked its stars for fakes yet.

  • Active OK

    Last change today.

  • Licence OK

    Apache-2.0: you can use it for free, also in a commercial product. Keep the licence notice.

Quick checks from public data. They help, but they are no guarantee.

What it is

A Python library that emulates bit-exact FP8 tensor-core GEMMs, matching the output of torch._scaled_mm and Transformer Engine on NVIDIA H100 PCIe or RTX 4060 GPUs, so results can be reproduced on a CPU or another CUDA GPU. It warns or raises for unsupported cases.

Who it's for

Researchers and engineers who need reproducible FP8 GEMM results across GPUs, such as PyTorch or Transformer Engine users

How to use it

Install

pip install mmaemu

From its README. Check it there before running it.

Ask your AI to set it up

Paste this into Claude, ChatGPT or your coding assistant.

Help me install and set up astding/mmaemu in my project. Follow its README: https://github.com/astding/mmaemu. Explain each step and check it is safe before running anything.

Star curve

60From 0 to 60 stars between 15 Oct 2026 and 29 Oct 2026.

Get alerts for repos like this

We'll email you when something in Models & inference starts rising. Free, once a week, only what matches.

22,066 GitHub repos watched and ranked every hour. Figures as of 29 October 2026.

What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy

For maintainers

Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.

[![astding/mmaemu on RepoAlerts](https://repoalerts.com/badge/astding/mmaemu.svg)](https://repoalerts.com/repo/astding/mmaemu?ref=badge)
Share on X
  • KohakuBlueleaf/KohakUnlock

    Research repository on unlocking tensor-compute throughput on NVIDIA GPUs via firmware-level changes. It documents a Linux initramfs port for one TU102 card and reproduction notes for Ampere, with C s

    ResourceDev infrastructureC · 359 stars · +359 this week · 4 days old

  • NVIDIA/spark-local-inference

    A local inference server for NVIDIA SM120/SM121 GPUs aimed at long conversations, coding agents and repeated tool use. Models are prepared at build time with PyTorch, Transformers and FlashInfer, then

    AppModels & inferenceRust · 695 stars · +159 this week · 9 days old

  • patch-gg/crowdbricks

    Batched variant of NVIDIA MotionBricks that generates character motion for many characters in one TensorRT model call. It adds a batch dimension to the ONNX model, batched SOMA kernels, and a crowd ru

    LibraryAI agentsPython · 103 stars · +103 this week · 1 day old

  • haohervchb/Turing-unlock

    Research repository documenting a volatile, pre-OS tensor-compute unlock for an ASUS RTX 2080 Ti (TU102). It publishes EFI loader source, host-side tests, CUDA benchmarks and measured results showing

    ResourceModels & inferenceC · 128 stars · +126 this week · 7 days old

  • academa-labs/manimgx

    A Python animation engine that renders 2D and 3D math videos using Manim CE's API, with a Rust and wgpu GPU renderer. It exports 1080p60 MP4 files, runs in the browser via Pyodide and WebGPU, and supp

    Creative toolsPython · 2,282 stars · +279 this week · 23 days old

  • jesdga95/basalt

    A C++ local inference engine for the Qwen3.8-Flash-Next mixture-of-experts model on NVIDIA Blackwell GPUs (sm_120) under Linux and Windows. Experts that do not fit in VRAM are kept in system RAM, opti

    AppModels & inferenceC++ · 280 stars · +160 this week · 22 days old