Commit 0bf3b2e
committed
Update base for Update on "[Executorch][LLM] Use caching allocator for runner"
We observed that on iOS it improves perf by 6% because SDPA op does temp allocations.
No significant difference on android though.
Differential Revision: [D86120038](https://our.internmc.facebook.com/intern/diff/D86120038/)
[ghstack-poisoned]1 parent 6a0d471 commit 0bf3b2e
0 file changed
0 commit comments