swift15: runbook LIVE + deployed verification + vision probe law
This commit is contained in:
@@ -1,6 +1,6 @@
|
||||
# frank-primary — Radiance (StillDeadcode), Swift1.5 Qwen3.8-Flash-Next W4Dn8, 2× R9700 TP=2
|
||||
|
||||
**Status: STAGED — activates at the cutover below.** · **Host:** Dankserver (192.168.0.235) · **Port:** 7770 · **GPU:** 2× Radeon AI PRO R9700 (gfx1201), TP=2
|
||||
**Status: LIVE — deployed 2026-10-08 (main `3ca64e1`, e2e 33/33).** · **Host:** Dankserver (192.168.0.235) · **Port:** 7770 · **GPU:** 2× Radeon AI PRO R9700 (gfx1201), TP=2
|
||||
|
||||
The FP8-native era (`qwen4exp-fp8-native.rad`, 173.0 GiB, no-recipe convert)
|
||||
is replaced by a **GPTQ-calibrated 4-bit container** of
|
||||
@@ -140,10 +140,22 @@ MiB measured**); the serve size floor `FRANK_PRIMARY_RAD_MIN_MIB` moves
|
||||
summary is a coherent ordered index of the concatenated corpus
|
||||
(no repetition, no NaN-token garbage) — the depth-corruption class
|
||||
of 2026-10-04 is clean.
|
||||
- Fleet probes: PASS — vision (solid-red 512 px → "Red"), tool_calls
|
||||
(`{"expr":"23 * 47"}`), reasoning_effort xhigh/medium/low/high all
|
||||
200 (the Swift1.5 template accepts the full set), reasoning_content
|
||||
present, response_format json_object honoured.
|
||||
- Fleet probes: PASS, re-run on the deployed prod — vision (solid-red
|
||||
512 px → "Red"), tool_calls (`{"expr":"23 * 47"}`), reasoning_effort
|
||||
xhigh/medium/low/high all 200 (the Swift1.5 froggeric template accepts
|
||||
the full set), reasoning_content present, response_format json_object
|
||||
honoured. **Vision probe law:** budget ≥ 256 tokens and read
|
||||
`reasoning_content` as fallback — at 64 tokens thinking exhausts the
|
||||
budget and `content` comes back empty (the answer lands in the
|
||||
reasoning channel).
|
||||
- **Deployed verification (2026-10-08)**: `deploy.sh dankserver
|
||||
--service frank-primary` green incl. Playwright e2e 33/33; unit
|
||||
`active`, `/health` 200, `/v1/models` id `frank-primary` (the harness
|
||||
alias is the served-model-name, independent of the file — models.yml
|
||||
untouched). Deployed shape: fp8 KV (KLD-gate shape), spec depth 2,
|
||||
seqs 3, vram pair 26071/3543. Boot ledger: KV pool 3.46 GiB, expert
|
||||
pools 57.84 GiB, cards settled 1.41 GiB free, `serving on :7770`.
|
||||
Live decode probe (512 tokens, streamed, temp 0): ~190 t/s.
|
||||
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user