Lightning-AI/lightning-thunder

quantization: process tensors on meta device directly, maybe implement CPU quantization (if it is easy)

Open

#1,111 opened on 2024年9月6日

GitHub で見る
 (4 comments) (0 reactions) (0 assignees)Python (114 forks)github user discovery
good first issuetransforms

Repository metrics

Stars
 (1,460 stars)
PR merge metrics
 (PR metrics pending)

説明

Currently the BitsAndBytesLinearQuant4bit for submodule always calls bitsandbytes.functional.quantize_4bit. This is somewhat touchy for CPU tensors because quantize_4bit only works on GPU tensors but it is outright not so nice for meta tensors, where we only would need to get the right shapes.

https://github.com/Lightning-AI/lightning-thunder/blob/e64d347def39bb47101efafe4177adf9f77a63ec/thunder/transforms/quantization.py#L93-L103

コントリビューターガイド