Skip to content

server : fix warmup draft cache type#12446

Merged
ggerganov merged 1 commit intomasterfrom
ggg/server-fix-warmup-draft-cache-type
Mar 18, 2025
Merged

server : fix warmup draft cache type#12446
ggerganov merged 1 commit intomasterfrom
ggg/server-fix-warmup-draft-cache-type

Conversation

@ggerganov
Copy link
Copy Markdown
Member

fix #12436

Use F16 draft cache type during the warmup.

@ggerganov ggerganov merged commit 810e0af into master Mar 18, 2025
47 checks passed
@ggerganov ggerganov deleted the ggg/server-fix-warmup-draft-cache-type branch March 18, 2025 10:05
arthw pushed a commit to arthw/llama.cpp that referenced this pull request Mar 19, 2025
Seunghhon pushed a commit to Seunghhon/llama.cpp that referenced this pull request Apr 26, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Misc. bug: KV Cache seems to be initialized twice for the draft model?

2 participants