Extend Qwen30 JIT readiness for latency surface

runs/frontier-fidelity-envelope-v1/run_qwen30_latency_case_real_surface.sh

@@ -16,7 +16,8 @@ CLIENT="${RUNNER_DIR}/qwen30_exact_trace_client.py"
 PREFILL_CLIENT="${RUNNER_DIR}/../frontier-phase-factorial-v0/qwen30_prefill_client.py"
 VENV_ROOT="${VENV_ROOT:-/tmp/wjh/venvs/vllm-0.20.0-cu129-profiler-v1}"
 MODEL_ROOT="${MODEL_ROOT:-/home/admin/cpfs/wjh/models/Qwen/Qwen3-30B-A3B}"
-FLASHINFER_SHARED_WORKSPACE="${FLASHINFER_SHARED_WORKSPACE:-${OUT}/flashinfer-shared-workspace}"
+FLASHINFER_SHARED_WORKSPACE="${FLASHINFER_SHARED_WORKSPACE:-/tmp/wjh/flashinfer-workspace-vllm020-profiler-v1}"
+SERVER_READY_ATTEMPTS="${SERVER_READY_ATTEMPTS:-300}"
 PORT="${BASE_PORT:-8300}"
 
 case "${PREFIX_CACHING}" in
@@ -97,6 +98,7 @@ launch_config() {
       VENV_ROOT="${VENV_ROOT}" \
       MODEL_ROOT="${MODEL_ROOT}" \
       FLASHINFER_WORKSPACE_BASE="${FLASHINFER_SHARED_WORKSPACE}" \
+      SERVER_READY_ATTEMPTS="${SERVER_READY_ATTEMPTS}" \
       EXACT_TRACE_CLIENT="${CLIENT}" \
       timeout --signal=TERM --kill-after=60s 4200 bash "${RUNNER}" \
       > "${run_out}/launcher.stdout.log" 2> "${run_out}/launcher.stderr.log"