Stars
Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.
LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar
Skills for writing tilelang and debugging with CUDA toolkits.
Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels
🎨 The open-source Claude Design alternative. 🖥️ Local-first desktop app. 🖼️ Your coding agent becomes the design engine: prototypes, landing pages, dashboards, slides, images & video — real files, …
Assign issues to Claude Code, Codex, Cursor, and 17 more coding agents like teammates — open-source and self-hostable.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with C…
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
CUDA kernels for linear attention variants, written in CuTe DSL and CUTLASS C++.
AI agents running research on single-GPU nanochat training automatically
Tiny, Fast, and Deployable anywhere — automate the mundane, unleash your creativity
Byted PyTorch Distributed for Hyperscale Training of LLMs and RLs
Engine-agnostic LLM gateway in Rust. Full OpenAI & Anthropic API compatibility across vLLM, TRT-LLM, TokenSpeed, SGLang, OpenAI, Gemini & more. Industry-first gRPC pipeline, KV cache-aware routing,…
Fast inference from large lauguage models via speculative decoding
Machine Learning Engineering Open Book
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
[ECCV 2026 Oral] Implementation of "Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length"
"AI-Trader: 100% Fully-Automated Agent-Native Trading"
The official repo of Pai-Megatron-Patch for LLM & VLM large scale training developed by Alibaba Cloud.
"DeepCode: Open Agentic Coding (Paper2Code & Text2Web & Text2Backend)"
Efficient implementation of DeepSeek Ops (Blockwise FP8 GEMM, MoE, and MLA) for AMD Instinct MI300X