Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
senfu
's Collections
ToP
Budget Guidance
CommVQ
CommVQ
updated
Jun 9
CommVQ: Commutative Vector Quantization for KV Cache Compression
Upvote
-
senfu/Llama-3.1-8B-Instruct-CommVQ-2bit
9B
•
Updated
Jun 5
•
7
senfu/Llama-3.1-8B-Instruct-CommVQ-1bit
8B
•
Updated
Jun 9
•
7
senfu/Llama-3.1-8B-Instruct-CommVQ-1bit-codebook
Updated
Jun 9
senfu/Llama-3.1-8B-Instruct-CommVQ-2bit-codebook
Updated
Jun 9
Upvote
-
Share collection
View history
Collection guide
Browse collections