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Mark old 7-GPU and pre-5/13 docs as superseded.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

..

profile-driven-harness-design.md

Document profile-driven harness design

2026-05-12 21:09:29 +08:00

profile-driven-harness-implementation-20260512.md

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

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

qwen27b-chat-0-8k-ttft4s-tpot25-20260510.md

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

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

qwen27b-chat-0-8k-ttft4s-tpot25-gpu8-20260513.md

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

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

qwen235b-thinking-prefill-ttft-3s6s9s-20260514.md

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

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

qwen235b-thinking-prefill-ttft-20260510.md

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

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