Skip to content

bugfix: fix the problem of incorrect kv cache data format when enabli…#1203

Closed
longhui-z wants to merge 0 commit intojd-opensource:mainfrom
longhui-z:main
Closed

bugfix: fix the problem of incorrect kv cache data format when enabli…#1203
longhui-z wants to merge 0 commit intojd-opensource:mainfrom
longhui-z:main

Conversation

@longhui-z
Copy link
Copy Markdown
Contributor

…ng prefix cache feature(for deepseek v3 model).

Copy link
Copy Markdown
Contributor

@gemini-code-assist gemini-code-assist Bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code Review

This pull request updates model type checks to use prefix matching for "deepseek_v3" instead of exact equality. The review feedback suggests using rfind for a more idiomatic prefix check and recommends defining the model type string as a constant to comply with the project's naming conventions (Rule 18).

Comment thread xllm/core/runtime/worker_impl.cpp Outdated
Comment thread xllm/models/llm/npu/mtp_model_base.h Outdated
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.

1 participant