Update config for Llama-3.2-3B-Instruct-W4V8.mxq

Upload Llama-3.2-3B-Instruct-W4V8.mxq to main

chore: normalize mxq LFS patterns

chore: rename npu prefill chunk size

chore: update prefill chunk size

Upload Llama-3.2-3B-Instruct-W4V8.mxq to main

Update config mxq_path for Llama-3.2-3B-Instruct-W4V8.mxq

Upload Llama-3.2-3B-Instruct-W4V8.mxq to main

Upload Llama-3.2-3B-Instruct-W4V8.mxq to main

Upload Llama-3.2-3B-Instruct-W4V8.mxq (non-2026-02)

sync main to W4V8

rename Llama-3.2-3B-Instruct.mxq to Llama-3.2-3B-Instruct-W8.mxq

rename Llama-3.2-3B-Instruct.mxq to Llama-3.2-3B-Instruct-W8.mxq

Upload Llama-3.2-3B-Instruct.mxq

Create proxy_llama.py

Update config.json

Upload folder using huggingface_hub

Delete .gitignore

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Delete .gitignore

Update .gitignore

Update README.md

Upload folder using huggingface_hub

Update README.md

Update README.md

initial commit