SqueezeAILab/KVQuant
KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization
Python
Stargazers
- abacajsoftware eng building things
- amirgholamiBAIR, UC Berkeley
- Bionagato
- caoshiyiUC Berkeley
- chhzh123Cornell University
- costa-al@turing-machines
- darvid@atomweight
- DefTruthStatistics Department of JNU
- denisfitz57
- gj-raza
- HivaMohammadzadeh1San Francisco Bay Area
- HubHopDeepSeek
- IlyasMoutawwakil@huggingface
- joshuaminwookangUC Berkeley
- juvu
- kssteven418BAIR, UC Berkeley
- kugwzk
- liujingcsMonash University
- lucasjinrealGoogle
- MarsJacobsHanyang University
- mazzzystar
- Minami-su
- ndresSoacha
- rentainheIDEA
- RonanKMcGovernTrelis Research
- SakitsMIT, EECS
- sldStockholm, Stockholm County, Sweden
- SuhongMoonBerkeley AI Research
- timothyklim
- Trangle
- voladeltaThe Matrix
- wuyongyiLambdaX
- Xiuyu-LiUC Berkeley
- yingfengChina
- younesbelkada@huggingface
- zhijlXidian University