Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up
João André Gomes Marques's picture

João André Gomes Marques

jmarquex
1

AI & ML interests

None yet

Recent Activity

updated a model about 20 hours ago
jmarquex/nexusquant
updated a Space 2 days ago
jmarquex/nexusquant-demo
updated a collection 8 days ago
KV Cache Compression Methods
View all activity

Organizations

None yet

jmarquex 's collections 1

KV Cache Compression Methods
Methods for compressing the KV cache in transformer inference. E8 lattice, KVarN, TurboQuant, KIVI.
  • jmarquex/nexusquant

    Updated about 20 hours ago
  • Running
    Agents

    NexusQuant E8 KV Cache Demo

    🗜

    Generate text with and without KV cache compression

KV Cache Compression Methods
Methods for compressing the KV cache in transformer inference. E8 lattice, KVarN, TurboQuant, KIVI.
  • jmarquex/nexusquant

    Updated about 20 hours ago
  • Running
    Agents

    NexusQuant E8 KV Cache Demo

    🗜

    Generate text with and without KV cache compression

Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs