Gahow Wang 984eb1f325 Document 8-GPU harness ablation results for qwen27b and qwen235b prefill ...

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Mark old 7-GPU and pre-5/13 docs as superseded.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.

2026-05-16 21:23:16 +08:00

..

harness-ablation

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

2026-05-16 21:23:16 +08:00

qwen27b-chat-0-8k-7day-compare

docs: expand qwen27b 0-8k compare summary

2026-04-17 20:45:24 +08:00

qwen27b-chat-pd-colocation

Add qwen27b and qwen235b tuning notes

2026-04-11 12:07:42 +08:00

qwen30b-community-vllm020

Add open source project metadata

2026-05-06 21:18:21 +08:00

qwen235b-thinking-decode

Add open source project metadata

2026-05-06 21:18:21 +08:00

qwen235b-thinking-prefill

docs: add q235b prefill 0-32k tight summary

2026-04-18 16:10:29 +08:00

superpowers/plans

Add open source project metadata

2026-05-06 21:18:21 +08:00

aituner-harness-summary.md

Add open source project metadata

2026-05-06 21:18:21 +08:00

harness-tuning-progress.md

Document qwen27b harness convergence curve

2026-04-26 01:32:18 +08:00

qwen27b-chat-0-8k-current-config-fig18-20260506.md

Document qwen27b current config harness curve

2026-05-06 18:00:43 +08:00

qwen27b-chat-0-8k-harness-fig18.md

Document qwen27b harness convergence curve

2026-04-26 01:32:18 +08:00

qwen27b-chat-0-8k-setup-audit-20260506.md

Document qwen27b chat setup audit

2026-05-06 20:32:09 +08:00

qwen27b-chat-0-8k-tpot40-baseline-infeasible-20260507.md

Report latency stats for infeasible baseline

2026-05-08 11:10:34 +08:00

qwen235b-thinking-prefill-harness-20260427.md

Record qwen235b harness convergence test

2026-04-27 18:59:25 +08:00