Skip to content

Commit 1d6c70c

Browse files
kimishpatelkimishpatel
committed
Update base for Update on "[Executorch][llama] Enable quantized sdpa"
Enable leveraging quantized sdpa op when quantized kv cache is used. Instead of adding yet another arg, at the moment I have chosen to leverage quantize_kv_cache option. Differential Revision: [D71833064](https://our.internmc.facebook.com/intern/diff/D71833064/) [ghstack-poisoned]
1 parent 9e72771 commit 1d6c70c

0 file changed

File tree

    0 commit comments

    Comments
     (0)