Skip to content

Bug: [CANN] inference running result is garbled in debug running model for LM models who's type is Q4_0 class #9979

@leo-pony

Description

@leo-pony

What happened?

For CANN backend: inference running result is garbled in debug running model for LM models who's type is Q4_0 class

Name and Version

b3948

What operating system are you seeing the problem on?

No response

Relevant log output

No response

Metadata

Metadata

Assignees

Labels

Ascend NPUissues specific to Ascend NPUsmedium severityUsed to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)

Type

No type

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions