Skip to content

chore(v038): coderabbit fixes on droplet driver, watcher, bench fence #148

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
vaaraio merged 1 commit into from
May 27, 2026
Merged

chore(v038): coderabbit fixes on droplet driver, watcher, bench fence #148

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion bench/vaara-bench-v0.38.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -83,7 +83,7 @@ quantization flag when the model config already declares

## Reproduction recipe

```
```bash
PYTHONPATH=src .venv/bin/python scripts/eval_v038_phase1.py \
--bundle src/vaara/data/adversarial_classifier_v8.joblib \
--threshold 0.9006 \
Expand Down
5 changes: 3 additions & 2 deletions scripts/v038_droplet_run.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -58,8 +58,9 @@ else
--host 0.0.0.0 --port "${PORT}" \
--max-model-len 8192 \
--enforce-eager \
--gpu-memory-utilization 0.92 \
>"${LOG_DIR}/vllm_llama33.log" 2>&1
--gpu-memory-utilization 0.92

nohup docker logs -f vllm-llama33 >"${LOG_DIR}/vllm_llama33.log" 2>&1 &

echo "[v038] waiting for /v1/models (max 30 min)"
for i in $(seq 1 180); do
Expand Down
8 changes: 5 additions & 3 deletions scripts/v038_local_watcher.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,14 +30,16 @@ GEN_LOCAL="tests/adversarial/generated"
GEN_REMOTE="/root/v038-out/"
LOG_REMOTE="/root/vllm-logs"

SSH_OPTS=(-o BatchMode=yes -o ConnectTimeout=10 -o ServerAliveInterval=15 -o ServerAliveCountMax=2)

mkdir -p "${WATCH_DIR}" "${GEN_LOCAL}"

ts() { date -u +%FT%TZ; }
note() { echo "[$(ts)] $*" | tee -a "${WATCH_DIR}/progress.log"; }

note "watcher start; droplet=${DROPLET} target=${N_PER_CAT}/category interval=${INTERVAL_SEC}s suffix=${OUT_SUFFIX}"

if ! ssh -o BatchMode=yes -o ConnectTimeout=10 "${DROPLET}" 'echo ok' >/dev/null 2>&1; then
if ! ssh "${SSH_OPTS[@]}" "${DROPLET}" 'echo ok' >/dev/null 2>&1; then
note "FATAL: ssh ${DROPLET} 'echo ok' failed. Check droplet IP + key auth."
exit 2
fi
Expand Down Expand Up @@ -72,12 +74,12 @@ while true; do
fi
done

vllm_model=$(ssh -o BatchMode=yes "${DROPLET}" \
vllm_model=$(ssh "${SSH_OPTS[@]}" "${DROPLET}" \
"curl -sf http://localhost:8000/v1/models 2>/dev/null | grep -oE '\"id\"[[:space:]]*:[[:space:]]*\"[^\"]*\"' | head -1 | grep -oE '\"[^\"]*\"\$' | tr -d '\"'" \
2>/dev/null || echo "SSH_FAIL")
if [[ "$vllm_model" != "${EXPECTED_MODEL}" ]] && [[ "$vllm_model" != "SSH_FAIL" ]]; then
note "WARNING vllm_model='${vllm_model}' (expected ${EXPECTED_MODEL})"
ssh -o BatchMode=yes "${DROPLET}" "tail -20 ${LOG_REMOTE}/vllm_llama33.log" 2>&1 \
ssh "${SSH_OPTS[@]}" "${DROPLET}" "tail -20 ${LOG_REMOTE}/vllm_llama33.log" 2>&1 \
| tee -a "${WATCH_DIR}/progress.log" || true
fi

Expand Down