From 06d4c380b36685cc2f516b4c1098828f389a961a Mon Sep 17 00:00:00 2001
From: Gahow Wang <gahow.wang@gmail.com>
Date: Fri, 10 Apr 2026 17:43:02 +0800
Subject: [PATCH] Align qwen27b baseline proposal with topology study

---
 .../dash0_qwen27b_tight_slo_baseline_proposal.json     | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/configs/examples/dash0_qwen27b_tight_slo_baseline_proposal.json b/configs/examples/dash0_qwen27b_tight_slo_baseline_proposal.json
index 662a30d..8c40200 100644
--- a/configs/examples/dash0_qwen27b_tight_slo_baseline_proposal.json
+++ b/configs/examples/dash0_qwen27b_tight_slo_baseline_proposal.json
@@ -3,20 +3,18 @@
   "diagnosis": "This model uses a long-context hybrid stack and fp8 quantization. The safest first measurement is to preserve the existing warmup, hybrid-model, chunked-prefill, and prefix-caching behavior from run_qwen27b.sh, while keeping a conservative sequence cap.",
   "config_patch": {
     "env_patch": {
-      "VLLM_ATTENTION_BACKEND": "FLASH_ATTN",
-      "VLLM_ENABLE_TORCH_COMPILE": "1",
-      "VLLM_USE_FLASHINFER_SAMPLER": "0",
-      "VLLM_ENABLE_MODEL_RUNNER_WARMUP": "1"
+      "VLLM_ENABLE_TORCH_COMPILE": "1"
     },
     "flag_patch": {
       "tensor-parallel-size": 4,
+      "data-parallel-size": 1,
+      "expert-parallel-size": 1,
       "gpu-memory-utilization": 0.9,
       "block-size": 64,
       "max-num-batched-tokens": 8192,
       "max-num-seqs": 16,
       "enable-prefix-caching": true,
-      "enable-chunked-prefill": true,
-      "disable-cascade-attn": true
+      "enable-chunked-prefill": true
     }
   },
   "expected_effects": [