mirror of
https://github.com/hpcaitech/ColossalAI.git
synced 2025-06-26 15:32:22 +00:00
7172459e74
* [shardformer] implement policy for all GPT-J models and test * [shardformer] support interleaved pipeline parallel for bert finetune * [shardformer] shardformer support falcon (#4883) * [shardformer]: fix interleaved pipeline for bert model (#5048) * [hotfix]: disable seq parallel for gptj and falcon, and polish code (#5093) * Add Mistral support for Shardformer (#5103) * [shardformer] add tests to mistral (#5105) --------- Co-authored-by: Pengtai Xu <henryxu880@gmail.com> Co-authored-by: ppt0011 <143150326+ppt0011@users.noreply.github.com> Co-authored-by: flybird11111 <1829166702@qq.com> Co-authored-by: eric8607242 <e0928021388@gmail.com>
18 lines
490 B
Python
18 lines
490 B
Python
from .chunk import ChunkManager, TensorInfo, TensorState, search_chunk_configuration
|
|
from .gemini_ddp import GeminiDDP
|
|
from .gemini_mgr import GeminiManager
|
|
from .gemini_optimizer import GeminiAdamOptimizer, GeminiOptimizer
|
|
from .utils import get_static_torch_model
|
|
|
|
__all__ = [
|
|
"GeminiManager",
|
|
"TensorInfo",
|
|
"TensorState",
|
|
"ChunkManager",
|
|
"search_chunk_configuration",
|
|
"GeminiDDP",
|
|
"get_static_torch_model",
|
|
"GeminiAdamOptimizer",
|
|
"GeminiOptimizer",
|
|
]
|