Stars
Lightning-fast, on-device TTS — running natively via ONNX.
Slim(toolkit): Don't change anything in your container image and minify it by up to 30x (and for compiled languages even more) making it secure too! (free and open source)
The Triton Inference Server provides an optimized cloud and edge inferencing solution.
CUDA Templates and Python DSLs for High-Performance Linear Algebra
PNG decoding and encoding library in pure Rust
Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
SGLang is a fast serving framework for large language models and vision language models.
A high-throughput and memory-efficient inference and serving engine for LLMs
Efficent platform for inference and serving local LLMs including an OpenAI compatible API server.
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.
[CVPR 2025] OVO-Bench: How Far is Your Video-LLMs from Real-World Online Video Understanding?
Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!
A configurable, terminal based MPD Client with album art support via various terminal image protocols
🔥 🔥 🔥 Open Source JIRA, Linear, Monday, and Asana Alternative. Plane helps you track your issues, epics, and cycles the easiest way on the planet.
Rust GUI components for building fantastic cross-platform desktop application by using GPUI.
A radically modular HTML/CSS rendering engine
Rust bindings to https://github.com/k2-fsa/sherpa-onnx
High-quality multi-lingual text-to-speech library by MyShell.ai. Support English, Spanish, French, Chinese, Japanese and Korean.
Fullstack app framework for web, desktop, and mobile.