Update README.md

v1.1.x: optional --int8 dynamic quant (CPU, ~2x smaller memory 708->325MB, identical output) + README note

v1.1: CPU support — pure-PyTorch lamba_cpu.py (decode-cache, no Triton) + lamba_rag.py --device cpu + README/notebook

fix: repo adi guncellendi (notebook REPO)

Update README.md

Update README.md

Update README.md

add LAMBA_Inference.ipynb

add lamba_rag.py

add README.md

Mamba-3 GPU wheels

Upload tokenizer/tokenizer.model with huggingface_hub

LAMBA V1.0 weights

initial commit