Hugging Face's logo

harshithsaiv
/
kv-cache-compression

English
quantization
kv-cache
llm-inference
cuda
triton
memory-efficient
mitral
llama
inference-optimization
4-bit precision
mixed-precision
Model card Files
xet
 Community
kv-cache-compression / visualize_long_context.py

Commit History

  1. feat: complete 4-method benchmark with honest memory reporting⁠

    harshithsaiv
    0774ec2

  2. feat: adding visualization for longer context

    harshithsaiv
    eec6c0e