Featured Tool

vLLM

High-throughput LLM serving engine with PagedAttention

Open SourceSelf HostedOffline CapableGPU Required (16GB+ VRAM)
0.0 (0)

About

vLLM is a library for high-throughput LLM inference and serving, originally developed at UC Berkeley's Sky Computing Lab. Its PagedAttention algorithm manages attention key and value memory efficiently to raise throughput and reduce waste. It supports more than 200 model architectures from Hugging Face, continuous batching, quantization, tensor parallelism, and an OpenAI-compatible server. Apache 2.0 licensed and maintained by a large contributor community.

Reviews (0)

Leave a Review

No reviews yet. Be the first to review!

Details

Price
Free
Platform
Local/Desktop
Difficulty
Intermediate (3/5)
License
Apache-2.0
Minimum VRAM
16 GB
Added
Jan 29, 2026

Related Tools

Open-source ChatGPT alternative that runs 100% offline on your computer.

Open SourceSelf HostedOffline
Beginner
Featured

Port of Meta's LLaMA model in C/C++ for efficient CPU inference

Open SourceSelf HostedOffline
Intermediate

Fast LLM inference on consumer GPUs using neuron-aware sparse computation.

Open SourceSelf HostedOfflineGPU 4GB+
Advanced

Easy-to-use local AI inference with built-in web UI and API.

Open SourceSelf HostedOffline
Beginner

High-performance LLM inference engine forked from vLLM with extra features.

Open SourceSelf HostedOfflineGPU 8GB+
Intermediate

Minimalist machine learning framework for Rust focused on performance and serverless inference.

Open SourceSelf HostedOffline
Intermediate
Browse all LLM Inference & Serving tools