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

..

__init__.py

[Feat] Diffusion Model(PixArtAlpha/StableDiffusion3) Support (#5838)

2024-07-08 16:02:07 +08:00

glide_llama.py

[Inference/SpecDec] Support GLIDE Drafter Model (#5455)

2024-04-10 11:07:52 +08:00

nopadding_baichuan.py

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

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

nopadding_llama.py

Pass inference model shard configs for module init

2024-06-07 08:33:52 +00:00

pixart_alpha.py

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

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

stablediffusion3.py

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

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