ascend: align attention mask to 32bytes #7
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
yao-fengchen
approved these changes
Aug 19, 2024
jinminxi104
approved these changes
Aug 19, 2024
zhaochaoxing
pushed a commit
that referenced
this pull request
Aug 20, 2024
jinminxi104
pushed a commit
that referenced
this pull request
Aug 20, 2024
yao-fengchen
pushed a commit
that referenced
this pull request
Aug 22, 2024
yao-fengchen
pushed a commit
that referenced
this pull request
Aug 22, 2024
jinminxi104
pushed a commit
that referenced
this pull request
Aug 22, 2024
pdx1989
added a commit
that referenced
this pull request
Aug 23, 2024
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.
yao-fengchen
pushed a commit
that referenced
this pull request
Aug 23, 2024
yao-fengchen
added a commit
that referenced
this pull request
Sep 2, 2024
* support ascend using infer_ext * fix(ascend): make infer_ext using TND format q,k,v in paged_token_attention * support ascend using infer_ext * feat: support ascend moe_gating_topk_softmax * feat: change infer_ext ops function param order (#2) * ascend: align attention mask to 32bytes (#7) * fix attn args (#9) * fix: expand shape of attn_mask (#10) * feat: udpate infer_ext ops interface (#13) * rename infer_ext to dlinfer * format code * Support internlm 2.5 (#14) * refactor ascend pagedattention * fix ascend apply_rotary_pos_emb * fix import dlinfer (#16) * fix: fix rms_norm params (#18) * fix sync on ascend --------- Co-authored-by: chenchiyu <[email protected]> Co-authored-by: CyCle1024 <[email protected]> Co-authored-by: Wei Tao <[email protected]> Co-authored-by: jinminxi104 <[email protected]> Co-authored-by: pdx1989 <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
CANN建议attention mask对齐到32字节以保证性能。
如上脚本运行，如果attention mask没有对齐到32bytes则会报错，对齐到32bytes则通过