Skip to content

feat(llama-cpp-localai-paged): paged KV cache llama.cpp backend + cross-request prefix sharing + GB10 decode optimization [WIP]#10462

Draft
localai-bot wants to merge 128 commits into
masterfrom
worktree-feat+paged-attention
Draft

feat(llama-cpp-localai-paged): paged KV cache llama.cpp backend + cross-request prefix sharing + GB10 decode optimization [WIP]#10462
localai-bot wants to merge 128 commits into
masterfrom
worktree-feat+paged-attention

docs(paged): speedup-hunt C section + final RANK + PLAN synthesis

6bfca14
Select commit
Loading
Failed to load commit list.

Select a check to view from the sidebar