fastpath oversized basic test outputs

worklogs/remote_scripts/start_platform_245k_repro.sh

@@ -0,0 +1,112 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+OUT="${1:-/root/work/logs/platform_245k_repro_20260715_01}"
+PORT="${PORT:-1111}"
+MODEL="${MODEL:-/root/public-storage/models/Qwen/Qwen3.6-35B-A3B}"
+mkdir -p "$OUT"
+
+cd /root
+export PYTHONPATH=/usr/local/corex/lib64/python3/dist-packages
+export LD_LIBRARY_PATH=/usr/local/corex/lib64:/usr/local/iluvatar/lib64:/usr/local/openmpi/lib
+export PATH=/usr/local/corex/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/local/openmpi/bin
+export VLLM_ENGINE_ITERATION_TIMEOUT_S=3600
+export MOE_NATIVE=1
+export CHUNK_PARALLEL=1
+export PREFIX_FLASH=1
+export RMSNORM_NATIVE=1
+export LOOP1_NATIVE=1
+export PROF_TRACE=0
+export PROF_MOE_SUMMARY=0
+export MOE_DECODE_NATIVE=0
+
+python3 - <<'PY'
+import os
+import signal
+import subprocess
+import time
+
+out = subprocess.check_output(["ps", "-eo", "pid,args"], text=True)
+pids = []
+for line in out.splitlines():
+    if "vllm.entrypoints.openai.api_server" in line or "VllmWorkerProcess" in line:
+        pid = int(line.strip().split(None, 1)[0])
+        if pid != os.getpid():
+            pids.append(pid)
+print("stop_pids", pids)
+for pid in pids:
+    try:
+        os.kill(pid, signal.SIGTERM)
+    except ProcessLookupError:
+        pass
+time.sleep(8)
+out = subprocess.check_output(["ps", "-eo", "pid,args"], text=True)
+left = []
+for line in out.splitlines():
+    if "vllm.entrypoints.openai.api_server" in line or "VllmWorkerProcess" in line:
+        pid = int(line.strip().split(None, 1)[0])
+        left.append(pid)
+for pid in left:
+    try:
+        os.kill(pid, signal.SIGKILL)
+    except ProcessLookupError:
+        pass
+print("sigkill_pids", left)
+PY
+
+echo "[repro] gpu before start" | tee "$OUT/driver.log"
+LD_LIBRARY_PATH=/usr/local/corex-3.2.3/lib64:/usr/local/corex/lib64:/usr/local/corex/lib:/usr/local/iluvatar/lib64 \
+  /usr/local/corex/bin/ixsmi | tee -a "$OUT/driver.log"
+
+nohup python3 -m vllm.entrypoints.openai.api_server \
+  --model "$MODEL" \
+  --served-model-name llm \
+  --host 0.0.0.0 \
+  --port "$PORT" \
+  --max-model-len 245000 \
+  --enforce-eager \
+  --gpu-memory-utilization 0.9 \
+  --trust-remote-code \
+  -tp 4 \
+  --max-num-seqs 1 \
+  --disable-log-requests \
+  --disable-frontend-multiprocessing \
+  --max-num-batched-tokens 16384 \
+  --enable-chunked-prefill \
+  --max-seq-len-to-capture 245000 \
+  --enable-auto-tool-choice \
+  --tool-call-parser qwen3_coder \
+  --reasoning-parser qwen3 \
+  --enable-prefix-caching \
+  --chat-template /workspace/chat_template_multi_system.jinja \
+  > "$OUT/server.log" 2>&1 &
+
+echo $! > "$OUT/server.pid"
+echo "[repro] server_pid=$(cat "$OUT/server.pid")" | tee -a "$OUT/driver.log"
+
+for i in $(seq 1 90); do
+  if python3 - <<PY >/dev/null 2>&1
+import urllib.request
+urllib.request.urlopen("http://127.0.0.1:${PORT}/health", timeout=2).read()
+PY
+  then
+    echo "[repro] health_ok_after_checks=$i" | tee -a "$OUT/driver.log"
+    exit 0
+  fi
+  if ! kill -0 "$(cat "$OUT/server.pid")" 2>/dev/null; then
+    echo "[repro] server_exited_at_check=$i" | tee -a "$OUT/driver.log"
+    tail -160 "$OUT/server.log" | tee -a "$OUT/driver.log"
+    exit 2
+  fi
+  if [ $((i % 6)) -eq 0 ]; then
+    echo "[repro] waiting_check=$i" | tee -a "$OUT/driver.log"
+    tail -10 "$OUT/server.log" | tee -a "$OUT/driver.log"
+    LD_LIBRARY_PATH=/usr/local/corex-3.2.3/lib64:/usr/local/corex/lib64:/usr/local/corex/lib:/usr/local/iluvatar/lib64 \
+      /usr/local/corex/bin/ixsmi | head -45 | tee -a "$OUT/driver.log"
+  fi
+  sleep 10
+done
+
+echo "[repro] health_timeout" | tee -a "$OUT/driver.log"
+tail -220 "$OUT/server.log" | tee -a "$OUT/driver.log"
+exit 3