RH-RunningHub/MiniMax-H3-MultiGPU-Lightning

MiniMax-H3 multi-GPU inference acceleration: ~12x on 8x RTX 6000D (step distillation + SageAttention2 + Cache-DiT + torch.compile, TP2+Ulysses4 on sglang)

Language modelsPython

1.4 Steady Magnitude out of 10. Star growth looks organic. Data as of September 14, 2026.

Open on Seismograph Open on GitHub

About the project

Multi-GPU inference acceleration recipe for MiniMax H3 video generation using step distillation, SageAttention2, Cache-DiT and torch.compile on SGLang, up to ~12x on 8x RTX 6000D.

Useful for

Deploy the recipe on your own multi-GPU rig to speed up 5-second video generation
Swap RH's private weights for public acceleration LoRAs and reproduce the full inference workflow
Compare TP2+Ulysses4 with other parallelism setups for latency and memory

README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.

Why it’s trending

3 stars today.
The repository is 6 days old and already has 74 stars.
Top new repositories this week: #200.
Recent forks include notable developers: @kaelzhang (386 followers).

Stars per day

Bars are daily stars, the line is the usual pace. Red marks spike days.

Numbers

Total stars: 74
Stars in a day: 3
Forks: 11
Issues and pull requests: 1
Watchers: 1
Language: Python
License: Apache-2.0
Created: September 7, 2026
Last push: September 10, 2026

Star trust

Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.

These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.

Spotted in

September 13, 2026Top new repositories this week: #185

README badge

Paste it into your README — the badge shows the current magnitude and links to this page.

[![Seismograph](https://gitnova.dev/badge/RH-RunningHub/MiniMax-H3-MultiGPU-Lightning.svg?lang=en)](https://gitnova.dev/en/r/RH-RunningHub/MiniMax-H3-MultiGPU-Lightning)

Similar projects

6.1
JustVugg/colibri
A pure-C, zero-dependency inference engine for running large MoE models (744B–2.8T parameters) on consumer hardware by treating VRAM, RAM, and storage as a single multitier hierarchy and streaming experts from disk.

BreakoutLanguage modelsC+1,048 stars in a day
5.7
asgeirtj/system_prompts_leaks
A collection of extracted system prompts from Anthropic, OpenAI, Google, xAI and others — the hidden instructions chatbots receive before a user's first message.

BreakoutLanguage modelsJavaScript+428 stars in a day
5.1
kennethwolters/litelm
A lightweight litellm alternative: routes LLM calls across 19 providers and translates message formats in ~2,900 lines with two dependencies, without proxy, caching, or cost tracking.

Early signalLanguage modelsPython+9 stars in a day
5.0
MiaAI-Lab/DeepSeek-v4.1-Flash-EXL3-2x-DGX-Sparks
A local EXL3 2.9 bpw checkpoint of DeepSeek-V4.1-Flash (196 GiB, 39 shards) served via an OpenAI-compatible vLLM API on a 2x NVIDIA GB10 (DGX Spark) kit with tensor-parallel 2. Includes DSpark speculative decoding and…

Early signalLanguage modelsPython+81 stars in a day
4.8
unclecode/crawl4ai
Open-source web crawler and scraper that turns pages into clean, LLM-ready Markdown for RAG, agents and data pipelines. Runs via Python API, CLI and Docker with no API keys.

BreakoutLanguage modelsPython+411 stars in a day
4.5
Edge0-AI/Edge0
An open-source streaming MoE inference framework: expert weights are offloaded from SSD on demand while a trained prerouter predicts routing ahead of time. Runs on Apple Silicon via MLX and ships with two ready-to-run…

CoolingLanguage modelsPython+118 stars in a day