torchchat
torchchat copied to clipboard
[FEATURE REQUEST] Create sdpa_with_kv support for float16, bfloat16
see run here => https://github.com/pytorch/torchchat/actions/runs/8872459136/job/24356835073
We can always upcast to make things pass, but if there's an easy way to build float16 and bfloat16 flavors (iPad Pro has M-series chip with bfloat support AFAIRK?), that'd be rad.