transformers
4c0b8abe - Quantize each tensor on the fly through its member's op

Commit
6 days ago
Quantize each tensor on the fly through its member's op The loader takes the quantize op before it reads the tensor. The host's op finds the member when it runs. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Parents
Loading