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

GenomaLabs-com
/
kv-cache-eviction-mla

Transformers
kv-cache
h2o
mla
long-context
inference-optimization
deepseek
kimi
Model card Files Files and versions
xet
Community

Instructions to use GenomaLabs-com/kv-cache-eviction-mla with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use GenomaLabs-com/kv-cache-eviction-mla with Transformers:

    # Load model directly
    from transformers import AutoModel
    model = AutoModel.from_pretrained("GenomaLabs-com/kv-cache-eviction-mla", device_map="auto")
  • Notebooks
  • Google Colab
  • Kaggle
kv-cache-eviction-mla / results
18.1 kB
Ctrl+K
Ctrl+K
  • 4 contributors
History: 4 commits
GENOMA LABS / research
Claude Opus 4.7 (1M context)
Day 1 of 7-day Kimi K2.6 + RULER 128K sprint: transformers 5.x port + real-weights install validation
95298f5 5 months ago
  • kimi_layer_eviction_demo.csv
    7.07 kB
    B3a-pivot: real Kimi K2.6 weights demo - eviction policy validated on actual MLA attention distribution 5 months ago
  • validate_eviction_random_init.csv
    11 kB
    Day 1 of 7-day Kimi K2.6 + RULER 128K sprint: transformers 5.x port + real-weights install validation 5 months ago