feat(llama.cpp): upgrade and use libmtmd #5379
Merged
Conversation
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
Signed-off-by: Ettore Di Giacinto <[email protected]>
Signed-off-by: Ettore Di Giacinto <[email protected]>
Signed-off-by: Ettore Di Giacinto <[email protected]>
✅ Deploy Preview for localai ready!
To edit notification comments on pull requests, go to your Netlify project configuration. |
Signed-off-by: Ettore Di Giacinto <[email protected]>
Closed
Signed-off-by: Ettore Di Giacinto <[email protected]>
Signed-off-by: Ettore Di Giacinto <[email protected]>
Signed-off-by: Ettore Di Giacinto <[email protected]>
Signed-off-by: Ettore Di Giacinto <[email protected]>
Signed-off-by: Ettore Di Giacinto <[email protected]>
Signed-off-by: Ettore Di Giacinto <[email protected]>
Signed-off-by: Ettore Di Giacinto <[email protected]>
mudler
force-pushed
the
libmtmd-grpc-driftfree
branch
from
4488367 to
dd381f8
Compare
Signed-off-by: Ettore Di Giacinto <[email protected]>
mudler
added a commit
to mudler/llama.cpp
that referenced
this pull request
Jun 3, 2025
This is in order to improve maintainability and re-usability by downstream projects such as LocalAI (see mudler/LocalAI#5379 for context). The context server is a struct that can be re-used quite heavily by other communication protocols. For instance, LocalAI uses the context server on top of gRPC rather than having a REST API. This change improves overall re-usability by isolating the REST API to its own file so the context server can be imported easily. Signed-off-by: mudler <[email protected]>
mudler
added a commit
to mudler/llama.cpp
that referenced
this pull request
Jun 3, 2025
This is in order to improve maintainability and re-usability by downstream projects such as LocalAI (see mudler/LocalAI#5379 for context). The context server is a struct that can be re-used quite heavily by other communication protocols. For instance, LocalAI uses the context server on top of gRPC rather than having a REST API. This change improves overall re-usability by isolating the REST API to its own file so the context server can be imported easily. Signed-off-by: mudler <[email protected]>
1 task
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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.
Description
Latest llama.cpp release bring various API changes among super exciting features (thanks 🫶 @ngxson and @ggerganov!) , this called a completely rewrite of our grpc server to avoid drift with upstream.
The new implementation now is (almost) on par with what's on llama.cpp master, but now keeping things in sync its much easier.
Notes for Reviewers
In a next round, would be cool to upstream some architectural changes (like splitting the main server) from the http server, reducing even more maintenance on LocalAI's side.
#5368
Supersedes #5365
Signed commits