Xuanlei Zhao f71e63b0f3 [moe] support optimizer checkpoint (#5015) ... * Refactor MoE Manager setup method * unshard optim ckpt * optim io * update transformer version * update requirements * update ckpt * update ckpt * update ckpt * fix engine * fix engine		2023-11-08 15:07:03 +00:00
..
modeling	[Inference] Fix bug in ChatGLM2 Tensor Parallelism (#5014)	2023-11-07 15:01:50 +08:00
policies	[Inference] Fix bug in ChatGLM2 Tensor Parallelism (#5014)	2023-11-07 15:01:50 +08:00
__init__.py	[misc] update pre-commit and run all files (#4752)	2023-09-19 14:20:26 +08:00
batch_infer_state.py	[Pipeline inference] Combine kvcache with pipeline inference (#4938)	2023-10-27 16:19:54 +08:00
engine.py	[moe] support optimizer checkpoint (#5015)	2023-11-08 15:07:03 +00:00
kvcache_manager.py	[Inference] Dynamic Batching Inference, online and offline (#4953)	2023-10-30 10:52:19 +08:00