server : implement cancellable request #11285
Merged
Conversation
This file contains 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
ggerganov
reviewed
Jan 18, 2025
| } | ||
|
|
||
| if (result == nullptr) { | ||
| i--; // retry |
There was a problem hiding this comment.
For i == 0 this will underflow
There was a problem hiding this comment.
It will be i++ as soon as we call continue anyway, so should not be a big problem. But anw I changed i to int, to be more explicit about the case where it can be negative.
(Also, i is not used anywhere inside the loop body, so I assume that it's safe to make it an int here)
ggerganov
approved these changes
Jan 18, 2025
anagri
pushed a commit
to BodhiSearch/llama.cpp
that referenced
this pull request
Jan 26, 2025
* server : implement cancellable request * fix typo * httplib 0.18.5 * fix i underflow
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Close #9273
Related to yhirose/cpp-httplib#2022
For requests that can take long time like completions or embeddings, the queue will unblock HTTP thread every 1 second to check for the status of HTTP connection.
Because this is done at HTTP thread, it will not affect the performance of inference thread, while still maintaining thread-safety requirement.