| .. |
|
__init__.py
|
[shardformer] init shardformer code structure (#3731)
|
2023-07-04 16:05:01 +08:00 |
|
auto_policy.py
|
[shardformer] fix chatglm implementation (#5644)
|
2024-04-25 14:41:17 +08:00 |
|
base_policy.py
|
[shardformer] refactor pipeline grad ckpt config (#5646)
|
2024-04-25 15:19:30 +08:00 |
|
bert.py
|
[Shardformer] add assert for num of attention heads divisible by tp_size (#5670)
|
2024-04-29 18:47:47 +08:00 |
|
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
|
[Shardformer] add assert for num of attention heads divisible by tp_size (#5670)
|
2024-04-29 18:47:47 +08:00 |
|
chatglm2.py
|
[shardformer] fix chatglm implementation (#5644)
|
2024-04-25 14:41:17 +08:00 |
|
falcon.py
|
[Shardformer] add assert for num of attention heads divisible by tp_size (#5670)
|
2024-04-29 18:47:47 +08:00 |
|
gpt2.py
|
[Shardformer] add assert for num of attention heads divisible by tp_size (#5670)
|
2024-04-29 18:47:47 +08:00 |
|
gptj.py
|
[Shardformer] add assert for num of attention heads divisible by tp_size (#5670)
|
2024-04-29 18:47:47 +08:00 |
|
llama.py
|
[hotfix] Fix KV Heads Number Assignment in KVCacheManager (#5695)
|
2024-05-07 23:13:14 +08:00 |
|
mistral.py
|
[Shardformer] add assert for num of attention heads divisible by tp_size (#5670)
|
2024-04-29 18:47:47 +08:00 |
|
opt.py
|
[Shardformer] add assert for num of attention heads divisible by tp_size (#5670)
|
2024-04-29 18:47:47 +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 |
f9afe0addd