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

2024-10-10 14:34:45 +08:00

..

backends

[Inference] Fix flash-attn import and add model test (#5794)

2024-06-12 14:13:50 +08:00

layers

[Feat] Distrifusion Acceleration Support for Diffusion Inference (#5895)

2024-07-30 10:43:26 +08:00

models

[Feat] Distrifusion Acceleration Support for Diffusion Inference (#5895)

2024-07-30 10:43:26 +08:00

policy

[shardformer] fix linear 1d row and support uneven splits for fused qkv linear (#6084)

2024-10-10 14:34:45 +08:00

__init__.py

[doc] updated inference readme (#5343)

2024-02-02 14:31:10 +08:00