Skip to content

fix prefix caching#307

Open
yao-fengchen wants to merge 4 commits intoDeepLink-org:mainfrom
yao-fengchen:prefix_caching
Open

fix prefix caching#307
yao-fengchen wants to merge 4 commits intoDeepLink-org:mainfrom
yao-fengchen:prefix_caching

Conversation

@yao-fengchen
Copy link
Copy Markdown
Contributor

No description provided.

@jinminxi104
Copy link
Copy Markdown
Collaborator

add a testcase to ci, for testing mixed prefill_with_kvcache and prefill_with_kvcache. (ex: chunked prefill size = 2k; 3 prompts length are 3k,0.2k, 0.2k

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.

2 participants