mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-11-04 09:32:00 +00:00
9731134296
* server: tests: add models endpoint scenario * server: /v1/models add some metadata * server: tests: add debug field in context before scenario * server: tests: download model from HF, add batch size * server: tests: add passkey test * server: tests: add group attention params * server: do not truncate prompt tokens if self-extend through group attention is enabled * server: logs: do not truncate log values * server: tests - passkey - first good working value of nga * server: tests: fix server timeout * server: tests: fix passkey, add doc, fix regex content matching, fix timeout * server: tests: fix regex content matching * server: tests: schedule slow tests on master * server: metrics: fix when no prompt processed * server: tests: self-extend add llama-2-7B and Mixtral-8x7B-v0.1 * server: tests: increase timeout for completion * server: tests: keep only the PHI-2 test * server: tests: passkey add a negative test
13 lines
192 B
Bash
Executable File
13 lines
192 B
Bash
Executable File
#!/bin/bash
|
|
|
|
set -eu
|
|
|
|
if [ $# -lt 1 ]
|
|
then
|
|
# Start @llama.cpp scenario
|
|
behave --summary --stop --no-capture --exclude 'issues|wrong_usages|passkey' --tags llama.cpp
|
|
else
|
|
behave "$@"
|
|
fi
|
|
|