You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

Jianghai 69cd7e069d [Inference] ADD async and sync Api server using FastAPI (#5396) ... * add api server * fix * add * add completion service and fix bug * add generation config * revise shardformer * fix bugs * add docstrings and fix some bugs * fix bugs and add choices for prompt template		7 months ago
..
__init__.py	[shardformer, pipeline] add `gradient_checkpointing_ratio` and heterogenous shard policy for llama (#5508)	8 months ago
grad_ckpt_config.py	[shardformer] refactor pipeline grad ckpt config (#5646)	7 months ago
shard_config.py	[sync] resolve conflicts of merging main	7 months ago
sharder.py	[nfc] fix typo colossalai/shardformer/ (#5133)	11 months ago
shardformer.py	[Inference] ADD async and sync Api server using FastAPI (#5396)	7 months ago
utils.py	[pipeline] update shardformer policy	1 year ago