server: move server-context to its own cpp|h #17595
Merged
+3,833
−3,664
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
ngxson
commented
Nov 29, 2025
tools/server/server-context.h
Outdated
Comment on lines
54
to
71
| struct server_slots_t { | ||
| ~server_slots_t(); | ||
| std::vector<server_slot*> data; | ||
| size_t size() const { return data.size(); } | ||
| server_slot & operator[](size_t idx) { return *(data[idx]); } | ||
| server_slot & operator[](size_t idx) const { return *(data[idx]); } | ||
| void clear(); | ||
| server_slot & create(); | ||
| struct iterator { | ||
| typename std::vector<server_slot*>::iterator it; | ||
| iterator(typename std::vector<server_slot*>::iterator i) : it(i) {} | ||
| server_slot & operator*() { return **it; } | ||
| iterator & operator++() { ++it; return *this; } | ||
| bool operator!=(const iterator& other) const { return it != other.it; } | ||
| }; | ||
| iterator begin() { return iterator(data.begin()); } | ||
| iterator end() { return iterator(data.end()); } | ||
| }; |
This comment was marked as outdated.
This comment was marked as outdated.
Sorry, something went wrong.
Collaborator
Author
There was a problem hiding this comment.
Nevermind, I think pimpl will be the cleaner way (and also easier for us, in case we need to add a new utility function into server_context)
Will implement this in my next commit
Collaborator
Author
There was a problem hiding this comment.
Implemented in 9a7b4f3 :
server_contextis moved toserver_context_impl(just renaming struct, the code is left untouched)- the new
server_contextonly expose: init(), load_model(), start_loop(), terminate()
@ggerganov Would be nice if you can review it in a short time frame (ideally before #17470 as some conflicts are inevitable). Thanks!
ngxson
force-pushed
the
xsn/create_server_context
branch
from
22039aa to
9a7b4f3
Compare
ggerganov
approved these changes
Nov 29, 2025
Collaborator
Author
|
Nice, thanks for the speedy review! |
ngxson
force-pushed
the
xsn/create_server_context
branch
from
5f7b502 to
c5f8cdf
Compare
Open
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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.
Extracted part of the changes in #17554 into this dedicated PR, just in case something goes wrong it's easier to trace back.
Compare to the proposed approach in the mentioned PR, which simply move everything to
.h, this PR do some extra thing:git mv, so that auto-merge can be more happy (I hope so, will need to test)server-context.h; so for example,server_slotis now a private implementationserver_context, consolidate everything into 4 main functions:init(),load_model(),start_loop(),terminate()This should allow easier integration of server inside CLI, while allow downstream to incorporate server as a library (cc @bandoti , probably pre-cursor to llamax)