Support cogvlm.

Optimize cogvlm performance.

Patch cogvlm language part.

Remove some redundant code.

Remove some changes.

Remove some variables.

feat: change infer_ext ops function param order (#2)

feat: support ascend qwen2 and qwen2_moe (#6)

* feat: support ascend qwen2 and qwen2_moe

* fix: fix ascend mixtral

ascend: align attention mask to 32bytes (#7)

fix attn args (#9)

fix: expand shape of attn_mask (#10)

Fix list.

Author: pdx1989