Files
ColossalAI/colossalai/inference/tensor_parallel/modeling/_utils.py
Jianghai ce7ade3882 [inference] chatglm2 infer demo (#4724)
* add chatglm2

* add

* gather needed kernels

* fix some bugs

* finish context forward

* finish context stage

* fix

* add

* pause

* add

* fix bugs

* finish chatglm

* fix bug

* change some logic

* fix bugs

* change some logics

* add

* add

* add

* fix

* fix tests

* fix
2023-09-22 11:12:50 +08:00

11 lines
405 B
Python

"""
Utils for model inference
"""
from colossalai.kernel.triton.copy_kv_cache_dest import copy_kv_cache_to_dest
def copy_kv_to_mem_cache(layer_id, key_buffer, value_buffer, context_mem_index, mem_manager):
copy_kv_cache_to_dest(key_buffer, context_mem_index, mem_manager.key_buffer[layer_id])
copy_kv_cache_to_dest(value_buffer, context_mem_index, mem_manager.value_buffer[layer_id])
return