💂
Highlights
- Pro
Lists (1)
Starred repositories
Code for udm14.com, a site with an easily-accessible AI-free Google search. This has a CC0 license so consider the code public domain.
Light, fluffy, and always free - The AWS Local Emulator alternative
Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.
Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.
droast - a dockerfile linter that actually has opinions 🔥
LMCache: Supercharge Your LLM with the Fastest KV Cache Layer
MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.
TurboQuant+ KV cache compression for vLLM. 3.8x smaller KV cache, same conversation quality. Fused CUDA kernels with automatic PyTorch fallback.
Tile primitives for speedy kernels
FlashInfer: Kernel Library for LLM Serving
Use git-praise to find out who to thank for that magical piece of code.
JAX implementation of OpenAI's Whisper model for up to 70x speed-up on TPU.
Algorithm powering the For You feed on X
A collection of notebooks/recipes showcasing usecases of open-source models with Together AI.
Apache Fluss is a streaming storage built for real-time analytics.
Specification and documentation for the Universal Commerce Protocol (UCP)
Database connectivity API standard and libraries for Apache Arrow
TritonBench: Benchmarking Large Language Model Capabilities for Generating Triton Operators
A utility to query metrics from Hitachi Vantara block storage and transfer them to graphite backend
Fast, robust Google Flights scraper (API) for Python. (Probably)
A feature-rich command-line audio/video downloader