From 3541065675cde0d56a7af0c760c7dd42be8bd708 Mon Sep 17 00:00:00 2001
From: Gahow Wang <gahow.wang@gmail.com>
Date: Mon, 15 Jun 2026 22:40:42 +0800
Subject: [PATCH] Speed up 27B TP A/B: request_timeout 180s, search.high 0.125

The wide 0.5 range made TP1 (low-capacity) waste many infeasible high-theta probes,
and the 900s request timeout made overloaded probes drain hung requests for 15min
each. Cap drain at 180s and bound the search to where the boundaries actually are.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---
 configs/examples/dash0_qwen27b_tp_ab.json | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/configs/examples/dash0_qwen27b_tp_ab.json b/configs/examples/dash0_qwen27b_tp_ab.json
index ee2ceda..7900667 100644
--- a/configs/examples/dash0_qwen27b_tp_ab.json
+++ b/configs/examples/dash0_qwen27b_tp_ab.json
@@ -20,7 +20,7 @@
     "port": 18082,
     "healthcheck_path": "/v1/models",
     "ready_timeout_s": 900,
-    "request_timeout_s": 900,
+    "request_timeout_s": 180,
     "launch_args": [
       "serve",
       "/home/admin/resource/model/464482ce/qwen3.5-27b/256k-0223-internal"
@@ -156,9 +156,9 @@
   },
   "search": {
     "low": 0.0,
-    "high": 0.5,
+    "high": 0.125,
     "tolerance": 0.001,
-    "max_probes": 7,
+    "max_probes": 6,
     "sample_seed": 20260325
   },
   "llm": {