Skip to content

[CPU: Bugfix] fix the problem mentioned in #4454 #4552

Open
Sherlockzhangjinge wants to merge 3 commits into
alibaba:masterfrom
Sherlockzhangjinge:RVV/Bugfix
Open

[CPU: Bugfix] fix the problem mentioned in #4454 #4552
Sherlockzhangjinge wants to merge 3 commits into
alibaba:masterfrom
Sherlockzhangjinge:RVV/Bugfix

Conversation

@Sherlockzhangjinge

Copy link
Copy Markdown
Contributor

Description

complete the PR that is closed in #4454
I have rebased this PR onto the latest master and resolved the merge conflicts caused by the changes already merged through #4359.

Specifically:

Kept both #include <sys/types.h> (from master) and #include "Int8FunctionsOpt.h" as suggested.
Preserved the bias_z fix by changing its type from const float* to const int32_t* and using the explicit integer-to-float conversion path, avoiding the incorrect pointer cast in the previous implementation.
Verified that the PR now applies cleanly on top of the current master branch.

The PR has been force-pushed after the rebase. Please take another look when convenient. Thanks!

Module

Type

  • Feature
  • Bugfix
  • Perf
  • Refact
  • Style
  • Doc
  • Test
  • Chore

Checklist

  • Commit message follows [Module:Type] Description format
  • Code compiles without errors
  • Tested on relevant platform(s)
  • No unrelated format or style changes included

Sherlockzhangjinge and others added 2 commits June 17, 2026 17:41
…thWiseInt8AddBiasScaleUnit which causse the error below:

不能在初始化时将 const int32_t* const 转换为 const float*

Signed-off-by: Jixingguang <1955992348@qq.com>

Signed-off-by: Sherlockzhangjinge <zjgzhangjinge@outlook.com>

Signed-off-by: lyd1992 <liuyudong@iscas.ac.cn>
Signed-off-by: Jixingguang <1955992348@qq.com>

Signed-off-by: Sherlockzhangjinge <zjgzhangjinge@outlook.com>

Signed-off-by: lyd1992 <liuyudong@iscas.ac.cn>
@wangzhaode wangzhaode self-assigned this Jun 18, 2026
Comment thread source/backend/cpu/riscv/rvv/MNNFloat2Int8.cpp Outdated
Comment thread source/backend/cpu/riscv/rvv/MNNLineDepthWiseInt8AddBiasScaleUnit.cpp Outdated
@wangzhaode wangzhaode added the awaiting contributor Waiting for contributor to address review comments or rebase label Jun 18, 2026
@wangzhaode

Copy link
Copy Markdown
Collaborator

There are unresolved merge conflict markers left in the diff:

  • source/backend/cpu/riscv/rvv/MNNFloat2Int8.cpp (line 10-14)
  • source/backend/cpu/riscv/rvv/MNNLineDepthWiseInt8AddBiasScaleUnit.cpp (line 23-27)

Please resolve these conflicts and force-push again. The code won't compile as-is.

Signed-off-by: Jixingguang <1955992348@qq.com>

Signed-off-by: Sherlockzhangjinge <zjgzhangjinge@outlook.com>

Signed-off-by: lyd1992 <liuyudong@iscas.ac.cn>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

awaiting contributor Waiting for contributor to address review comments or rebase

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants