GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.
- llm-inference
- ai-chat
Repository Index
47,133 repositories indexed
1–23 of 23 · Most stars
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
Find secrets with Gitleaks 🔑
TranslatedThis project aims to share the technical principles of large models and practical experience (large model engineering, large model application deployment).
- llm
- llm-inference
- llm-serving
- llm-training
20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud.
- llm
- llmops
- model-inference
- fine-tuning
OpenVINO™ is an open source toolkit for optimizing and deploying AI inference
- inference
- deep-learning
- openvino
- ai
A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.
- avx2
- c99
- cpu-inference
- deep-learning
TranslatedOpen-source manuscript of 《深入理解 AI Infra：量化分析与系统设计》 (In-Depth Understanding of AI Infra: Quantitative Analysis and System Design), by 李博杰 (Li Bojie): starting from hardware constraints and model architecture, it quantitatively derives the system design of LLM inference and training. Includes the full text of the book, a PDF, and companion calculation tools and experiments
- accelerator
- ai-infra
- ai-infrastructure
- book
Superduper: End-to-end framework for building custom AI applications and agents.
- ai
- mlops
- torch
- transformers
An open coding agent for your terminal, built by a community collective rather than a company. Bring your own model, keep your code on your machine, and owe nothing to anyone.
Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent, 150k-262k context. vLLM patches, requant pipeline, benchmarks.
- kv-cache
- llm-inference
- local-llm
- quantization
Project Maya - run GLM-5.3-Flash (321B MoE), DeepSeek-V4.1-Flash-1017 (748B MoE) and MiniMax-M3.1-Flash (428B MoE) privately on your own GPU(s), from one card to 16, NVIDIA or AMD, Linux or Windows. Engine, server, dashboard, OpenAI- and Anthropic-compatible API, quant tools.
A local inference engine for Apple silicon, built around the model.
- apple-silicon
- coding-agents
- llm-inference
- macos
Your Cheat Sheet For AI Engineering Interviews at Top AI Companies - Questions and Answers.
- ai
- ai-engineering
- ai-interview
- ai-interview-questions
Official SGLang x Datawhale course on LLM inference: understand inference, build a mini-sglang from scratch, then read the real SGLang source and land your first PR. Available in English and Chinese.
Official Inference Code of EAGLE-4
- eagle
- gpu
- llm-inference
- sglang
Run a 105 GB AI model on a Mac that can't hold it. Qwen3.8-Flash-Next 4-bit, streamed from SSD on 16–64 GB Apple Silicon Macs. Fully native Swift, MLX and Metal. Offline, no Python. CLI, Swift library, and Ollama/OpenAI/Anthropic APIs. Works with Claude Code and Codex.
- apple-silicon
- llm
- llm-inference
- local-llm
Xolotl (formerly Strata-DSV4.1): run DeepSeek-V4.1-Flash, all 552B, as a local coding agent on one gaming PC (RTX 4090 + 90 GB RAM) at up to ~27 tok/s, 512K context, October 1017 builds included. Plus GLM-5.3-Flash and Qwen3.8. MoE experts tiered across VRAM, pinned RAM and NVMe; OpenAI + Anthropic API.
Fast, exact inference for StartLux-Decision models on NVIDIA GPUs: the released GGUF files on int8 and 4-bit tensor cores, behind the /v1/systemone API, with up to 5.3× lower latency than vLLM in FP8 and bit-identical answers.
- calibration
- cuda
- cuda-graphs
- decision-making
Translated🐋 Complete guide in Russian: how to install and run DeepSeek locally (V4, R1) on PC, Mac and server — Ollama, llama.cpp, LM Studio, vLLM, Open WebUI, API, RAG, agents, fine-tuning, best tips and tricks
- ai-agents
- deepseek
- deepseek-r1
- deepseek-v4
Feel how fast a local LLM runs before you buy the hardware
Legend of Elya — N64 game with a real 6.36M-parameter ternary transformer on the VR4300 MIPS III CPU. Zelda-style dungeon, AI NPCs, byte-level inference at 1.23 tok/s scalar / 2.19 tok/s on the RSP overlay (measured under ares, never on silicon). Built with libdragon.