A high-throughput and memory-efficient inference and serving engine for LLMs
Repository Index
47,133 repositories indexed
1–22 of 22 · Most stars
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
- pytorch
- speech-recognition
- paraformer
- punctuation
Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services
Nano vLLM
Android in docker solution with noVNC supported, video recording, mcp server and AI-agent
- docker-android
- android
- android-emulator
- novnc
Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent with full horsepower. Maintained by Orchestra Research.
- ai
- ai-research
- claude
- claude-code
✍🏻 Source Code Deep Dives, System Design & Engineering Blogs | Halfrost-Field 冰霜之地：源码解析、系统设计与工程实践笔记
- ios
- objective-c
- swift
- javascript
LMCache: Supercharge Your LLM with the Fastest KV Cache Layer
[SIGMOD'27] Easy Data Preparation with latest LLMs-based Operators and Pipelines.
- data
- data-cleaning
- data-pipelines
- data-processing
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
Open decision models from 0.8B to 27B: a calibrated probability for every option in one pass, and a short thought only when unsure. Engine for vLLM, llama.cpp and MLX.
- agents
- calibration
- classification
- decision-making
Turn any LLM into a Jev-style decision model: typed decisions, real probabilities, no training. (continue updating, welcome any issue and PR request)
- calibration
- decision-model
- jev
- jev-model
Official Inference Code of EAGLE-4
- eagle
- gpu
- llm-inference
- sglang
Native vLLM serving for Jev decision models
Berth is a lightweight GPU resource manager written in Go. It controls which applications get access to your GPU, when they get it, and how that access is handed off.
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
Kubernetes operator for self-hosted LLM inference across a heterogeneous GPU fleet: NVIDIA CUDA, AMD Vulkan, and Apple Silicon Metal. Runtimes: llama.cpp, vLLM, TGI, mlx-server. Multi-GPU sharding, model caching, OpenAI-compatible endpoints. Apache-2.0, run across homelab and on-prem fleets, actively developed.
Medical LLM agent and MRI segmentation workspace built on PharmaLLM, with LangGraph, vLLM, and BEU-Net.
🐋 Полный гайд на русском: как установить и запустить DeepSeek локально (V4, R1) на ПК, Mac и сервере — Ollama, llama.cpp, LM Studio, vLLM, Open WebUI, API, RAG, агенты, fine-tuning, лучшие фишки
- ai-agents
- deepseek
- deepseek-r1
- deepseek-v4
ModelSphere is an open-source LLM inference infrastructure designed to make production-grade model serving simple, efficient, and continuously optimized.
Enterprise-grade platform to generate and execute Cypress, Playwright, WebdriverIO, and Appium end-to-end tests from natural language requirements. (Appium is experimental and requires external mobile infrastructure.)