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_sensitivity.py

Commit History

feat: calibration complete + sensitivity heatmap for Mistral-7B
8eabcbc

harshithsaiv commited on