A high-throughput and memory-efficient inference and serving engine for LLMs
Repository Index
47,133 repositories indexed
1–24 of 25 · Most stars
Inference code for Llama models
Complete API layer for private AI applications on local models: RAG, skills, tools, MCP, text-to-sql, and more. Works with any OpenAI-compatible inference server.
TranslatedLangchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and Llama) RAG and Agent app with langchain
- chatglm
- langchain
- llm
- knowledge-base
SGLang is a high-performance serving framework for large language models and multimodal models.
DeepInfer: High-performance, large-scale inference framework for DeepSeek models
LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar
A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations
Nano vLLM
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.
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
🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
- bloom
- deep-learning
- distributed-systems
- language-models
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
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
Official Inference Code of EAGLE-4
- eagle
- gpu
- llm-inference
- sglang
EdgeRock: Strong Reasoning at Constant Memory. Multimodal models with O(N) generation and O(1) persistent history. Inference and evaluation code.
AI Agent Identity and Access Management and Inference Firewall
- agent-identity
- ai-audit
- ai-firewall
- ai-gateway
Run many AI agents at once on your Mac, up to 3x faster.
- agents
- apple-silicon
- artificial-intelligence
- inference-acceleration
🧱 Experimental library for building inference engines
Our lightning-fast inference engine.
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
A Long-Horizon Benchmark for Self-Improving Inference Systems