huawei-csl/KVarN
KVarN is a native vLLM KV-cache quantization backend for your agents: 3-5x more context, throughput above FP16, and FP16-level accuracy. Calibration-free, one flag.
- Stars
- 511
- Forks
- 37
- Open issues
- 8
- Last push
- 4mo ago
About KVarN
KVarN is a free, open-source AI inference tool by huawei-csl, written mainly in Python. KVarN is a native vLLM KV-cache quantization backend for your agents: 3-5x more context, throughput above FP16, and FP16-level accuracy. Calibration-free, one flag. It has 511 GitHub stars and 37 forks, and was last updated 4mo ago. It's released under the Apache-2.0 license, a standard open-source license.
- License
- Apache-2.0
- Language
- Python
- Stars
- 511
- Last update
- 4mo ago
- Runs on Mac
- Not stated
- GPU
- Not stated
- Paid API key
- Not required
- Self-hostable
- Yes
Similar free tools
vllm95k stars · A high-throughput and memory-efficient inference and serving engine for LLMs
BentoML8.9k stars · The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more!
ai-infra-book6.9k stars · 《深入理解 AI Infra：量化分析与系统设计》（李博杰 著）开源书稿：从硬件约束和模型架构出发，量化推导 LLM 推理与训练系统设计。含全书正文、PDF、配套计算工具与实验
failproofai6.0k stars · Observability and enforcement for AI agent harnesses. Capture every run and runtime reliability with policy enforcement.
plano7.1k stars · Plano is an AI-native proxy server and data plane for agentic apps. Smart LLM routing, observability, agent orchestration, and guardrails so you stay focused on your agents core logic.
TensorRT-LLM15k stars · 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
KVarN FAQ
Is KVarN free?
Yes. KVarN is open source and free to use. It's released under the Apache-2.0 license, a standard open-source license.
Does KVarN run on a Mac?
The project doesn't say. Check its installation guide before you start.
Does KVarN need a GPU?
The project doesn't state hardware needs. AI models generally run much faster with a GPU.
Is KVarN still maintained?
It was last updated 4mo ago. Check recent issues on GitHub to judge how active it is.
What are alternatives to KVarN?
Similar free, open-source tools include vllm, BentoML, ai-infra-book, failproofai.