docs: add lessons-learned with all optimization insights

Covers: launchd management, Dell hub power, batch tuning, thread count per arch, KV cache quantization, MTP speculation, flash attention, router mode vs two-servers, context sizing, swap monitoring.
2026-07-10 02:33:30 +08:00
parent 3994e29cb0
commit cc10540e9e
2 changed files with 165 additions and 0 deletions
@@ -80,6 +80,11 @@ Trade-off: ~3-4s model load time when switching models.
 ## Contents

 - `docs/` — Full optimization journey with benchmarks at each step
+  - `01-problem.md` — Why two models on one GPU is slow
+  - `02-initial-setup.md` — The naive two-server setup
+  - `03-optimization-journey.md` — Every optimization we tried
+  - `04-lessons-learned.md` — Hard-won insights and discoveries
+  - `06-router-mode.md` — Router mode setup and config
 - `configs/` — Launchd plist, INI preset, utility scripts
 - `benchmarks/` — Before/after speed comparison data