Gahow Wang
445e491123
third_party/vllm/ now tracked in git for direct patch management.
Based on vLLM v0.18.1 release with one patch applied:
vllm/v1/core/sched/scheduler.py:
Replace fatal assert with graceful skip when KV transfer callback
arrives for an already-aborted request during PD disaggregated serving.
Future vLLM modifications should be made directly in third_party/vllm/
and committed normally. The patches/ directory is kept as documentation
of what changed from upstream.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
19 lines
385 B
Bash
19 lines
385 B
Bash
#!/bin/bash
|
|
|
|
# Usage: ./rerun_test.sh path/to/test.py::test_name
|
|
|
|
# Check if argument is given
|
|
if [ $# -lt 1 ]; then
|
|
echo "Usage: $0 path/to/test.py::test_name"
|
|
echo "Example: $0 tests/v1/engine/test_engine_core_client.py::test_kv_cache_events[True-tcp]"
|
|
exit 1
|
|
fi
|
|
|
|
TEST=$1
|
|
COUNT=1
|
|
|
|
while pytest -sv "$TEST"; do
|
|
COUNT=$((COUNT + 1))
|
|
echo "RUN NUMBER ${COUNT}"
|
|
done
|