| .. |
|
__init__.py
|
[shardformer] init shardformer code structure (#3731)
|
2023-07-04 16:05:01 +08:00 |
|
auto_policy.py
|
change command
|
2024-06-18 02:31:33 +00:00 |
|
base_policy.py
|
[shardformer] refactor pipeline grad ckpt config (#5646)
|
2024-04-25 15:19:30 +08:00 |
|
bert.py
|
change 'xxx if xxx else None' to 'xxx or None'
|
2024-06-18 03:32:42 +00:00 |
|
blip2.py
|
[Shardformer] add assert for num of attention heads divisible by tp_size (#5670)
|
2024-04-29 18:47:47 +08:00 |
|
bloom.py
|
change 'xxx if xxx else None' to 'xxx or None'
|
2024-06-18 03:32:42 +00:00 |
|
chatglm2.py
|
change 'xxx if xxx else None' to 'xxx or None'
|
2024-06-18 03:32:42 +00:00 |
|
command.py
|
change 'xxx if xxx else None' to 'xxx or None'
|
2024-06-18 03:32:42 +00:00 |
|
falcon.py
|
[Shardformer] Add parallel output for shardformer models(bloom, falcon) (#5702)
|
2024-05-21 11:07:13 +08:00 |
|
gpt2.py
|
change 'xxx if xxx else None' to 'xxx or None'
|
2024-06-18 03:32:42 +00:00 |
|
gptj.py
|
[shardformer] upgrade transformers to 4.39.3 (#5815)
|
2024-06-14 10:59:33 +08:00 |
|
llama.py
|
change 'xxx if xxx else None' to 'xxx or None'
|
2024-06-18 03:32:42 +00:00 |
|
mistral.py
|
[shardformer] upgrade transformers to 4.39.3 (#5815)
|
2024-06-14 10:59:33 +08:00 |
|
opt.py
|
[pre-commit.ci] auto fixes from pre-commit.com hooks
|
2024-05-07 07:07:09 +00:00 |
|
qwen2.py
|
[Shardformer]fix the num_heads assert for llama model and qwen model (#5704)
|
2024-05-10 15:33:39 +08:00 |
|
sam.py
|
[Shardformer] add assert for num of attention heads divisible by tp_size (#5670)
|
2024-04-29 18:47:47 +08:00 |
|
t5.py
|
[Shardformer] add assert for num of attention heads divisible by tp_size (#5670)
|
2024-04-29 18:47:47 +08:00 |
|
vit.py
|
[Shardformer] add assert for num of attention heads divisible by tp_size (#5670)
|
2024-04-29 18:47:47 +08:00 |
|
whisper.py
|
[Shardformer] add assert for num of attention heads divisible by tp_size (#5670)
|
2024-04-29 18:47:47 +08:00 |
d84d68601a