Woosuk KwonandGitHub c9d5b6d4a8 Replace FlashAttention with xformers (#70)

2023-05-05 02:01:08 -07:00

..

__init__.py

Support tensor parallel (#2)

2023-03-21 13:45:42 -07:00

activation.py

Optimize data movement (#20)

2023-04-02 00:30:17 -07:00

attention.py

Replace FlashAttention with xformers (#70)

2023-05-05 02:01:08 -07:00

gpt2.py

Add support for GPT-2 (#60)

2023-05-04 02:59:56 -07:00

gpt_neox.py

Add support for GPT-2 (#60)

2023-05-04 02:59:56 -07:00

input_metadata.py

Replace FlashAttention with xformers (#70)

2023-05-05 02:01:08 -07:00

layernorm.py

Add custom kernel for RMS normalization (#16)

2023-04-01 00:51:22 +08:00

llama.py

Replace FlashAttention with xformers (#70)

2023-05-05 02:01:08 -07:00

memory_analyzer.py

Replace FlashAttention with xformers (#70)

2023-05-05 02:01:08 -07:00

model_utils.py

Use dtype from model config & Add Dolly V2 (#63)

2023-05-04 03:05:37 -07:00

opt.py

Replace FlashAttention with xformers (#70)

2023-05-05 02:01:08 -07:00

sample.py

Add support for GPT-2 (#60)

2023-05-04 02:59:56 -07:00

utils.py

Support bfloat16 data type (#54)

2023-05-03 14:09:44 -07:00