← Back to List
⚠
Notice:This resource is provided by a third-party author. Please review the code with AI tools or manually before use to ensure security and compatibility.
RustMichael-A-Kuykendall/shimmy

shimmy

⚡ Pure-Rust WebGPU inference engine — OpenAI-API compatible, GGUF native, runs on any GPU. No Python. No llama.cpp. Single binary.

82.9/100
★ 5.4KForks: 510
View on GitHub →
Loading report...

Similar Projects

spiceai

83

A portable accelerated SQL query, search, and LLM-inference engine, written in Rust, for data-grounded AI apps and agents.

Rust★ 3.0K

kalosm

81

Instant, controllable, local pre-trained AI models in Rust

Rust★ 2.2K

rtk

90

CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

Rust★ 60.7K

llmfit

85

Hundreds of models & providers. One command to find what runs on your hardware.

Rust★ 27.7K
← Back to List