Qwen-7B-Chat / modeling_qwen.py

Commit History

update modeling_qwen.py
be72f02

yangapku commited on

update modeling_qwen.py
da8479a

yangapku commited on

update modeling_qwen.py
9cae423

yangapku commited on

update modeling_qwen.py
ffc5701

yangapku commited on

update
7f62181

yangapku commited on

remove fix-sized causal mask
2abd8e5

yangapku commited on

add kernel file check in modeling_qwen.py
03752a6

yangapku commited on

update modeling.py
013d71a

yangapku commited on

update modeling_qwen.py
8857f77

yangapku commited on

update batch inference
33ae36b

yangapku commited on

softmax_in_fp32
faf3ff6

yangapku commited on

update modeling_qwen.py
119ea93

yangapku commited on

update kernels
df4593d

yangapku commited on

update modeling_qwen.py
7df18a4

yangapku commited on

update modeling_qwen.py
21ed8f8

yangapku commited on

update kvcache
5255e1c

yangapku commited on

update readme
5a5440a

yangapku commited on

update batch infer
95b4d4c

yangapku commited on

update model
3ef28b8

yangapku commited on