mozempk/ggml-org-llama-cpp-mirror
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-10-11 07:20:33 +02:00
Code Issues Packages Projects Releases Wiki Activity

tests : adjust server string regex to also match m2 utlra results (#29648)

Browse Source
This commit is contained in:
Georgi Gerganov
2026-09-29 15:32:35 +03:00
committed by GitHub
parent 31385c9ceb
commit c85b92c69c
2 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/server/server-context.cpp
+1 -1
View File
@@ -3155,7 +3155,7 @@ private:
// TODO: support memory-less logits computation
if (slot.task->need_logits() && !llama_get_memory(ctx_tgt)) {
send_error(slot, "the current context does not logits computation. skipping", ERROR_TYPE_SERVER);
send_error(slot, "the current context does not support logits computation. skipping", ERROR_TYPE_SERVER);
slot.release();
return;
}
tools/server/tests/unit/test_completion.py
+1 -1
View File
@@ -148,7 +148,7 @@ def test_completion_stream_with_openai_library_stops():
if choice.finish_reason is None:
assert choice.text is not None
output_text += choice.text
assert match_regex("Sure, here's one for[\\s\\S]*", output_text), f'Unexpected output: {output_text}'
assert match_regex("Sure, here's one for[\\s\\S]*|Sure! Here's one for you[\\s\\S]*", output_text), f'Unexpected output: {output_text}'
@pytest.mark.parametrize("n_slots", [1, 2])