Skip to content

Conversation

@qyh111
Copy link
Contributor

@qyh111 qyh111 commented Sep 25, 2025

Purpose

What this PR does / why we need it?

Modifications

Does this PR introduce any user-facing change?

Test

How was this patch tested?

HaoLi980405 and others added 8 commits September 20, 2025 10:56
* deal bug

* gpu kpre and bug fixed

* deal bug

* deal bug

* deal bug

* clean code

* CI

* ci

---------

Co-authored-by: zbb200819 <1130072360@qq.com>
Co-authored-by: xujia <42216276@qq.com>
* increase q cache num

* deal 抢占bug

* ci

---------

Co-authored-by: xujia <42216276@qq.com>
Co-authored-by: zbb200819 <1130072360@qq.com>
…han configured (#196)

* kv_block_size as well as transferIoSize are calculated rather than configured

---------

Co-authored-by: root <fenghao78@huawei.com>
* cuda_topk

* 适配kv_block_size和IOsize

* clean code

* merge bug

* mutli-bs bug

* open_gsa deal

* add GSA description framework

* mutli bs deal

* clean code

* clean code

* gsa status deal

* add init file

---------

Co-authored-by: xujia <42216276@qq.com>
Co-authored-by: zbb200819 <1130072360@qq.com>
Co-authored-by: yxkyong <1033480555@qq.com>
…range (#204)

* md max seq len bug

* clean code

---------

Co-authored-by: zbb200819 <1130072360@qq.com>
@ygwpz ygwpz merged commit 1ab23bd into ModelEngine-Group:develop Sep 25, 2025
@qyh111 qyh111 deleted the dev_product_to_develop branch September 28, 2025 06:32
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

5 participants