docs(index): top-level link for the staged Swift15 runbook (seam 135)

This commit is contained in:
Frank committed 2026-10-07 04:42:36 -07:00
1 parent f747cb0dab
commit 2137080d1c
1 file changed
+5
+5
View File
@@ -182,6 +182,11 @@ The LLM inference fleet on the two hosts. Full index:
### Deployment and Topology ### Deployment and Topology
- [[deployment]] — unified deploy and update process for both servers - [[deployment]] — unified deploy and update process for both servers
- [[frank-primary-radiance-swift15-w4dn8]] — STAGED frank-primary runbook:
Swift1.5 Qwen3.8-Flash-Next BF16 → GPTQ-calibrated W4Dn8 `.rad` (radiance
1.0.13), gated on KLD ≤ 0.03 vs the BF16 container and decode ≥ 30.8 t/s;
activates by flipping `MODEL_FILE` in `scripts/frank-primary.env`, rollback
= revert that line (the FP8-native `.rad` stays on disk)
- [[frank-primary-radiance-qwen38-native-fp8]] — the ACTIVE frank-primary - [[frank-primary-radiance-qwen38-native-fp8]] — the ACTIVE frank-primary
runbook (2026-10-05): the StillDeadcode radiance engine (digest-pinned runbook (2026-10-05): the StillDeadcode radiance engine (digest-pinned
287 MiB image, libr4d gfx1201 kernels) serving the OFFICIAL 287 MiB image, libr4d gfx1201 kernels) serving the OFFICIAL