From d237fc2723c10524cdc957510df607b4f7c8d4f6 Mon Sep 17 00:00:00 2001
From: Gahow Wang <gahow.wang@gmail.com>
Date: Fri, 17 Apr 2026 20:45:24 +0800
Subject: [PATCH] docs: expand qwen27b 0-8k compare summary

---
 docs/qwen27b-chat-0-8k-7day-compare/README.md | 37 +++++++++++++++++++
 1 file changed, 37 insertions(+)

diff --git a/docs/qwen27b-chat-0-8k-7day-compare/README.md b/docs/qwen27b-chat-0-8k-7day-compare/README.md
index c6d9eaf..eba9145 100644
--- a/docs/qwen27b-chat-0-8k-7day-compare/README.md
+++ b/docs/qwen27b-chat-0-8k-7day-compare/README.md
@@ -34,6 +34,7 @@ qwen3.5-27b `chat` trace, `0~8k` input bucket, tuned-best vs baseline cross-day
 - Search:
   - binary search on `sampling_u`
   - `max_probes = 6`
+- Proposal model for tuned source: `codex / gpt-5.4`
 
 ## Run assets
 
@@ -43,6 +44,41 @@ qwen3.5-27b `chat` trace, `0~8k` input bucket, tuned-best vs baseline cross-day
 - Compare spec: `/home/admin/cpfs/wjh/aituner/aituner/.aituner-compare/specs/qwen27b_chat_0_8k_compare_dash1.json`
 - Tuned study root: `/home/admin/cpfs/wjh/aituner/aituner/.aituner-tight/dash0-qwen27b-tight-slo-10min-run9-chat-0-8k-codex-topology`
 
+## Tuned-source result
+
+- Best trial: `trial-0004`
+- Best config:
+  - `tensor-parallel-size=2`
+  - `data-parallel-size=1`
+- Best `sampling_u`: `0.013061523438`
+- Best request rate: `0.405 req/s`
+- Best request rate per GPU: `0.2025 req/s/gpu`
+- Best pass rate: `0.9629629629629629`
+
+Compared with the single-day baseline on `chat_w20260311_1000`:
+
+- `trial-0001`: `0.035 req/s`, `0.035 req/s/gpu`
+- `trial-0004`: `0.405 req/s`, `0.2025 req/s/gpu`
+- Raw throughput gain: `11.57x`
+- Per-GPU throughput gain: `5.79x`
+
+## 12-trial summary
+
+| Trial | Proposed config delta | Result |
+| --- | --- | --- |
+| `trial-0001` | baseline `TP1/DP1` | `0.0350 req/s`, `0.0350 req/s/gpu`, feasible |
+| `trial-0002` | `DP=2` | `0.1233 req/s`, `0.0617 req/s/gpu`, feasible |
+| `trial-0003` | `DP=4` | `0.1567 req/s`, `0.0392 req/s/gpu`, feasible |
+| `trial-0004` | `TP=2, DP=1` | `0.4050 req/s`, `0.2025 req/s/gpu`, feasible, best |
+| `trial-0005` | `trial-0004 + max-num-batched-tokens=16384` | infeasible |
+| `trial-0006` | `trial-0004 + max-num-seqs=24` | infeasible |
+| `trial-0007` | `trial-0004 + max-num-batched-tokens=12288` | infeasible |
+| `trial-0008` | `trial-0004 + block-size=32` | infeasible |
+| `trial-0009` | `trial-0004 + gpu-memory-utilization=0.93` | infeasible |
+| `trial-0010` | `trial-0004 + max-num-seqs=16, max-num-batched-tokens=6144` | infeasible |
+| `trial-0011` | `trial-0004 + enable-prefix-caching=false` | infeasible |
+| `trial-0012` | `trial-0004 + block-size=128` | infeasible |
+
 ## Aggregate result
 
 - Comparable wins: tuned `5`, baseline `0`
@@ -66,6 +102,7 @@ qwen3.5-27b `chat` trace, `0~8k` input bucket, tuned-best vs baseline cross-day
 
 ## Key insights
 
+- The tuned-source tuning itself was simple and topology-driven. The winning patch is only `TP1 -> TP2`; later runtime-only tweaks all failed to beat it.
 - This compare does not support the conclusion that the tuned config lacks generalization. Across the full 7-day slice, tuned wins every directly comparable window.
 - The two `incomparable` days are not execution failures. Baseline completed probing but never found a single feasible `sampling_u` under the target SLO, while tuned still found feasible operating points.
 - The tuned `TP=2, DP=1` shape is materially more robust than the `TP=1, DP=1` baseline for this `0~8k` chat bucket.