You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

Hongxin Liu 646b3c5a90 [shardformer] fix linear 1d row and support uneven splits for fused qkv linear (#6084) ... * [tp] hotfix linear row * [tp] support uneven split for fused linear * [tp] support sp for fused linear * [tp] fix gpt2 mlp policy * [tp] fix gather fused and add fused linear row		2 months ago
..
backends	[Inference] Fix flash-attn import and add model test (#5794)	6 months ago
layers	[Feat] Distrifusion Acceleration Support for Diffusion Inference (#5895)	4 months ago
models	[Feat] Distrifusion Acceleration Support for Diffusion Inference (#5895)	4 months ago
policy	[shardformer] fix linear 1d row and support uneven splits for fused qkv linear (#6084)	2 months ago
__init__.py	[doc] updated inference readme (#5343)	10 months ago