Qwen-14B / modeling_qwen.py

Commit History

add softmax_in_fp32
5e88027

yangapku commited on

update modeling_qwen.py
a6e3f8f

yangapku commited on

update kernels
fa98d75

yangapku commited on

update modeling_qwen.py
afc134b

yangapku commited on

update modeling_qwen.py
ea1640e

yangapku commited on

update kvcache
319ed0f

yangapku commited on

update readme
5ea0d35

yangapku commited on

update batch infer
33ba0fc

yangapku commited on

upload model
5cde1bb

yangapku commited on