KVQuant
[NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization
Implement efficient long context length processing for language models using low-precision data storage techniques.
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
Get an email alert on its next release or when it starts trending — never miss the moment.
Free · no card · unsubscribe anytime[NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization
KVQuant has 433 stars on GitHub. It has been forked 48 times. KVQuant is written mainly in Python. It has been in active development since 2024. Its main topics are compression, efficient-inference, efficient-model, large-language-models.
What is KVQuant?
[NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization
Is KVQuant open source?
KVQuant is an open-source project.
Is KVQuant free?
Yes. KVQuant is free and open source — you can use, modify and self-host it.
What language is KVQuant written in?
KVQuant is written mainly in Python.
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://olud.ai/project/squeezeailab-kvquant.html)
Measured from GitHub topics shared by both projects, weighted by how rare each topic is.