DeepSpeed

217b15d9 - tl.dot(a,b, trans_b=True) is not supported by triton2.0+ , updating this api (#4541)

tl.dot(a,b, trans_b=True) is not supported by triton2.0+ , updating this api (#4541) Stable Diffusion Inference with deepspeed inference engine works with this update with triton2.1 on A100 --------- Co-authored-by: Logan Adams <loadams@microsoft.com>