
framework
by mni-ml (organization)
A machine learning library with a TypeScript API and Rust backend. CUDA and WebGPU compatibility. Built to understand how ML frameworks and models work internally. (description from the project’s GitHub page)
Repository facts
- Stars
- 1,019
- Forks
- 131
- Open issues and pull requests
- 5
- Primary language
- Rust
- License
- MIT License (MIT)
- Owner
- mni-ml · Organization
- Created
- Jan 8, 2026
- Last push
- Apr 20, 2026
Topics
Related projects
Projects that share this one’s GitHub topics.
Rank 3,751: chelsea0x3b/dfdx
Deep learning in Rust, with shape checked tensors and neural networks
1,938 starsRustOther licenseLast push Jul 23, 2024
Rank 500: tracel-ai/burn
Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.
16,127 starsRustApache-2.0Last push Oct 16, 2026
Rank 7,564: pegainfer-project/pegainfer
Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2
724 starsRustApache-2.0Last push Oct 17, 2026
Rank 1,362: Michael-A-Kuykendall/shimmy
⚡ Pure-Rust WebGPU inference engine — OpenAI-API compatible, GGUF native, runs on any GPU. No Python. No llama.cpp. Single binary.
5,982 starsRustApache-2.0Last push Aug 30, 2026
Rank 5,635: fff-rs/juice
The Hacker's Machine Learning Engine
1,131 starsRustNo license file detectedLast push Jul 22, 2024
Rank 3,993: FL33TW00D/whisper-turbo
Cross-Platform, GPU Accelerated Whisper 🏎️
1,794 starsTypeScriptApache-2.0Last push Feb 27, 2024