gahow/aituner
0
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Document 8-GPU harness ablation results for qwen27b and qwen235b prefill

Browse Source 
Add completed experiment results from dash0 runs after 2026-05-13:
- qwen27b chat 0-8k: harness +118.6% over no-harness (0.2696 vs 0.1233 req/s/GPU)
- qwen235b prefill TTFT 3s/6s/9s: harness +76.8% (0.3921 vs 0.2217 req/s/GPU)

Mark old 7-GPU and pre-5/13 docs as superseded. Update implementation
log with completed run status.
This commit is contained in:
Gahow Wang
2026-05-16 21:23:16 +08:00
parent d0c89dac48
commit 984eb1f325
5 changed files with 223 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/harness-ablation/qwen27b-chat-0-8k-ttft4s-tpot25-20260510.md
View File

@@ -2,6 +2,8 @@
Date: 2026-05-10
**Superseded** by `qwen27b-chat-0-8k-ttft4s-tpot25-gpu8-20260513.md` (corrected 8-GPU setup). This document used `CUDA_VISIBLE_DEVICES=0,1,2,4,5,6,7` (7 GPUs) and is retained for reference only.
## Setup
- Host: `dash0` (`172.27.114.84`)