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.
ColossalAI/colossalai/inference/engine
Hongxin Liu 1cd7efc520
[inference] refactor examples and fix schedule (#5077)
1 year ago
..
modeling [Kernels]added flash-decoidng of triton (#5063) 1 year ago
policies [inference] Refactor inference architecture (#5057) 1 year ago
__init__.py [inference] update examples and engine (#5073) 1 year ago
engine.py [inference] refactor examples and fix schedule (#5077) 1 year ago
microbatch_manager.py [inference] Refactor inference architecture (#5057) 1 year ago