server : add kill switch when server is stuck#20277
Merged
Conversation
ggerganov
force-pushed
the
gg/server-kill-switch
branch
from
d1c1d32 to
8e840c0
Compare
Contributor
|
I managed to reproduce this reliably with gpt-oss-20b and 120b. Windows & Nvidia RTX 3090. repro.py The reproducer runs an agentic scenario, and then runs it again. The second run is what triggers the loop. Let me know if there's anything else I can provide. |
aldehir
approved these changes
Mar 9, 2026
aviallon
reviewed
Mar 9, 2026
| std::vector<server_slot> slots; | ||
|
|
||
| int slots_debug = 0; | ||
| int n_empty_consequtive = 0; |
bartowski1182
pushed a commit
to bartowski1182/llama.cpp
that referenced
this pull request
Mar 10, 2026
alam0rt
added a commit
to alam0rt/nix-config
that referenced
this pull request
Mar 14, 2026
…ound) - -c 32768 → 65536: openclaw compaction was failing at 41784 tokens - Remove --ctx-checkpoints 1: triggers empty-batch loop bug in b8255 which causes the kill-switch abort (server-context.cpp:2634) See: ggml-org/llama.cpp#20277
Ethan-a2
pushed a commit
to Ethan-a2/llama.cpp
that referenced
this pull request
Mar 20, 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
3 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
ref #20087 (comment)
Sometimes the server enters an infinite loop of empty batches. This change makes it easier to debug such cases.