Skip to content

enable_kv_cache_reuse don't work on Qwen L40 #2911

Open
@yeshihai

Description

@yeshihai

@yeshihai could you follow this guide to do your experiment?

Originally posted by @dominicshanshan in #2894

I followed the guide to conduct my experiment, but it didn't seem to work as expected. I initially set up everything according to the documentation. I understand you suggested checking the setup once more, which I did, but the issue persists. Could you kindly point out if there is anything I might have overlooked? I have tried to adhere to the instructions as closely as possible. Thank you for your assistance.

Metadata

Metadata

Assignees

Labels

InvestigatingKV-Cache Managementkv-cache management for efficient LLM inferencetriagedIssue has been triaged by maintainers

Type

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions