Lists (2)
Starred repositories
Fast, lossless LLM inference via dual-view diffusion decoding.
Fast LLM speculative inference server for consumer hardware.
🤗 ml-intern: an open-source ML engineer that reads papers, trains models, and ships ML models
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
Communicate with an LLM provider using a single interface
Open-Source Chrome extension for AI-powered web automation. Run multi-agent workflows using your own LLM API key. Alternative to OpenAI Operator.
LLMRouter: An Open-Source Library for LLM Routing
Official Code of Memento: Fine-tuning LLM Agents without Fine-tuning LLMs
Autonomous GPU Kernel Generation & Optimization via Deep Agents
FlashInfer: Kernel Library for LLM Serving
Dynamic Memory Management for Serving LLMs without PagedAttention
MemSifter: Offloading LLM Memory Retrieval via Outcome-Driven Proxy Reasoning
Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents
A collection of various llm pruning implementations, training code for GPUs & TPUs, and evaluation script.
Stanford NLP Python library for Representation Finetuning (ReFT)
Tiny, Fast, and Deployable anywhere — automate the mundane, unleash your creativity
Model compression toolkit engineered for enhanced usability, comprehensiveness, and efficiency.
Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice…
Compression for unit-norm embedding vectors using spherical coordinates
SimpleMem: Efficient Lifelong Memory for LLM Agents — Text & Multimodal
Atropos is a Language Model Reinforcement Learning Environments framework for collecting and evaluating LLM trajectories through diverse environments
Renderer for the harmony response format to be used with gpt-oss
A censorship-resistant platform where voices can’t be silenced, yet every report is verified with zero-knowledge proofs
Exploratory analysis of Bayesian models with Python
A browser extension for insights into GitHub, Gitee projects and developers.
An interactive TLS-capable intercepting HTTP proxy for penetration testers and software developers.