Qwen-14B-Chat / modeling_qwen.py

Commit History

add softmax_in_fp32
11d7120

yangapku commited on

update modeling_qwen.py
091b76e

yangapku commited on

update kernels
8da9235

yangapku commited on

update modeling_qwen.py
a5c7dd6

yangapku commited on

update modeling_qwen.py
ce2da0f

yangapku commited on

update kvcache
b7f19ef

yangapku commited on

update readme
25d6668

yangapku commited on

update batch infer
c17b80b

yangapku commited on

upload model
8291d90

yangapku commited on