..
__init__.py
[shardformer] init shardformer code structure ( #3731 )
2023-07-04 16:05:01 +08:00
auto_policy.py
[FP8] rebase main ( #5963 )
2024-08-06 16:29:37 +08:00
base_policy.py
[shardformer] refactor pipeline grad ckpt config ( #5646 )
2024-04-25 15:19:30 +08:00
bert.py
[fp8] support hybrid parallel plugin ( #5982 )
2024-08-12 18:17:05 +08:00
blip2.py
[fp8] support hybrid parallel plugin ( #5982 )
2024-08-12 18:17:05 +08:00
bloom.py
[fp8] support hybrid parallel plugin ( #5982 )
2024-08-12 18:17:05 +08:00
chatglm2.py
[fp8] support hybrid parallel plugin ( #5982 )
2024-08-12 18:17:05 +08:00
command.py
[fp8] support hybrid parallel plugin ( #5982 )
2024-08-12 18:17:05 +08:00
deepseek.py
[fp8]Moe support fp8 communication ( #5977 )
2024-08-09 18:26:02 +08:00
falcon.py
[fp8] support hybrid parallel plugin ( #5982 )
2024-08-12 18:17:05 +08:00
gpt2.py
[fp8] support hybrid parallel plugin ( #5982 )
2024-08-12 18:17:05 +08:00
gptj.py
[fp8] support hybrid parallel plugin ( #5982 )
2024-08-12 18:17:05 +08:00
llama.py
[fp8] support hybrid parallel plugin ( #5982 )
2024-08-12 18:17:05 +08:00
mistral.py
[fp8] support hybrid parallel plugin ( #5982 )
2024-08-12 18:17:05 +08:00
mixtral.py
[fp8]Moe support fp8 communication ( #5977 )
2024-08-09 18:26:02 +08:00
opt.py
[fp8] support hybrid parallel plugin ( #5982 )
2024-08-12 18:17:05 +08:00
qwen2.py
[fp8] support hybrid parallel plugin ( #5982 )
2024-08-12 18:17:05 +08:00
sam.py
[fp8] support hybrid parallel plugin ( #5982 )
2024-08-12 18:17:05 +08:00
t5.py
[fp8] support hybrid parallel plugin ( #5982 )
2024-08-12 18:17:05 +08:00
vit.py
[fp8] support hybrid parallel plugin ( #5982 )
2024-08-12 18:17:05 +08:00
whisper.py
[fp8] support hybrid parallel plugin ( #5982 )
2024-08-12 18:17:05 +08:00