From 77ca5767f5bf27ba0774edf1ded301c826d66277 Mon Sep 17 00:00:00 2001 From: noonghunna <10742901+noonghunna@users.noreply.github.com> Date: Fri, 1 May 2026 12:57:09 +0000 Subject: [PATCH] fix(launch): pass per-variant URL + CONTAINER to verify-full.sh (#20) AlexCPU's report: launch.sh selected the dual variant correctly, switch.sh booted the stack on port 8010 with container 'vllm-qwen36-27b-dual', then ran verify-full.sh without passing URL or CONTAINER. verify-full fell back to defaults (URL= http://localhost:8020, CONTAINER=vllm-qwen36-27b) and reported 6/8 checks failed because it was hitting the wrong endpoint. Fix: move the port-resolution block above the verify call, add a per-variant container-name mapping mirroring the port mapping, and pass URL + CONTAINER through to bash $VERIFY. Also surfaces the resolved values in the launcher output so users can see what the verify run is actually targeting. Co-Authored-By: Claude Opus 4.7 (1M context) --- scripts/launch.sh | 51 ++++++++++++++++++++++++++++++----------------- 1 file changed, 33 insertions(+), 18 deletions(-) diff --git a/scripts/launch.sh b/scripts/launch.sh index b0d38b1c..e5b589e0 100755 --- a/scripts/launch.sh +++ b/scripts/launch.sh @@ -198,24 +198,9 @@ echo "[launch] selected variant: ${VARIANT}" echo "" "$SWITCH" "$VARIANT" -if [[ $SKIP_VERIFY -eq 1 ]]; then - echo "[launch] --no-verify — skipping verify-full.sh" -else - echo "" - echo "[launch] running verify-full.sh against the new server..." - echo "" - bash "$VERIFY" || { - echo "" - echo "[launch] some checks failed — see hints above. Common cases:" - echo " - 'reasoning field empty' on llama.cpp = expected (parser gap, not a bug)" - echo " - 'Genesis patches' / 'MTP acceptance' skipped on llama.cpp = expected (vLLM-only checks)" - exit 1 - } -fi - -# Resolve the actual endpoint port the same way switch.sh does: -# explicit $PORT > per-variant default. Mirrors VARIANT_DEFAULT_PORT in -# switch.sh — keep in sync if you add a new variant. +# Resolve the actual endpoint port + container name the same way switch.sh +# does: explicit $PORT / $CONTAINER > per-variant default. Mirrors +# VARIANT_DEFAULT_PORT in switch.sh — keep in sync if you add a new variant. declare -A LAUNCH_DEFAULT_PORT=( [vllm/default]=8020 [vllm/long-vision]=8020 @@ -230,8 +215,38 @@ declare -A LAUNCH_DEFAULT_PORT=( [llamacpp/default]=8020 [llamacpp/concurrent]=8020 ) +declare -A LAUNCH_DEFAULT_CONTAINER=( + [vllm/default]=vllm-qwen36-27b + [vllm/long-vision]=vllm-qwen36-27b-long-vision + [vllm/long-text]=vllm-qwen36-27b-long-text + [vllm/bounded-thinking]=vllm-qwen36-27b-bounded-thinking + [vllm/tools-text]=vllm-qwen36-27b + [vllm/minimal]=vllm-qwen36-27b-minimal + [vllm/dual]=vllm-qwen36-27b-dual + [vllm/dual-turbo]=vllm-qwen36-27b-dual-turbo + [vllm/dual-dflash]=vllm-qwen36-27b-dual-dflash + [vllm/dual-dflash-noviz]=vllm-qwen36-27b-dual-dflash-noviz + [llamacpp/default]=llama-cpp-qwen36-27b + [llamacpp/concurrent]=llama-cpp-qwen36-27b-concurrent +) ENDPOINT_PORT="${PORT:-${LAUNCH_DEFAULT_PORT[$VARIANT]:-8020}}" ENDPOINT_URL="http://localhost:${ENDPOINT_PORT}" +ENDPOINT_CONTAINER="${CONTAINER:-${LAUNCH_DEFAULT_CONTAINER[$VARIANT]:-vllm-qwen36-27b}}" + +if [[ $SKIP_VERIFY -eq 1 ]]; then + echo "[launch] --no-verify — skipping verify-full.sh" +else + echo "" + echo "[launch] running verify-full.sh against the new server (URL=${ENDPOINT_URL}, CONTAINER=${ENDPOINT_CONTAINER})..." + echo "" + URL="$ENDPOINT_URL" CONTAINER="$ENDPOINT_CONTAINER" bash "$VERIFY" || { + echo "" + echo "[launch] some checks failed — see hints above. Common cases:" + echo " - 'reasoning field empty' on llama.cpp = expected (parser gap, not a bug)" + echo " - 'Genesis patches' / 'MTP acceptance' skipped on llama.cpp = expected (vLLM-only checks)" + exit 1 + } +fi echo "" echo "[launch] done. Endpoint: ${ENDPOINT_URL}"