mirror of
https://github.com/hpcaitech/ColossalAI.git
synced 2025-10-03 08:06:24 +00:00
* 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
11 lines
405 B
Python
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
|