server : enable multi-modal prompt caching#19877
Merged
Conversation
ngxson
approved these changes
Feb 25, 2026
|
I switched to gg/server-mtmd-prompt-cache, do git rebase master and build app. Confirm now prompt caching works! Note that I run with: no-mmproj-offload = on and not try without it VRAM usage is quite unstable for qwen3.5-27B, but this is not related to that issue. Thank you! |
f94fc71 to
dc4d447
Compare
|
Thank you very much for ggerganov effort to troubleshoot this problem I am using windows 10 b8157 release cuda 12.4 After this PR, text prompt processing is being handled by the CPU instead of the GPU, which is causing a significant slowdown. |
bartowski1182
pushed a commit
to bartowski1182/llama.cpp
that referenced
this pull request
Mar 2, 2026
ArberSephirotheca
pushed a commit
to ArberSephirotheca/llama.cpp
that referenced
this pull request
Mar 3, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
target #19849
cont #16391
We can now clone
server_tokensso re-enable host-memory prompt caching for multi-modal cases.