docs: frank-secondary at ubatch 2048 — Measured section, rollback ladder, fleet docs
23,120 used / 1,005 free at boot, 763 settled after a vision probe (encoder buffers resident). Rung cost 746 MiB, not the transferable 616 prediction. Prefill baseline 1,209 t/s @ 3,760 recorded; decode unchanged as the law says. 2048 = ceiling for this shape.
This commit is contained in:
Frank
@@ -27,9 +27,10 @@ timestamp: 2026-10-06
|
||||
> GiB assumed** (the drafter's KV is built against the target's full
|
||||
> context, not the 3-token proposal depth), paid for by the lighter
|
||||
> quant (−1.56 GiB). The late order dropped the per-slot window
|
||||
> 131,072 → **114,688** (Frank's 112k cap) and raised ubatch 512 →
|
||||
> 1024 — landing **1,751 MiB free**, back above the morning's number
|
||||
> with the prefill knob raised. This supersedes BOTH earlier 2026-10-05
|
||||
> 131,072 → **114,688** (Frank's 112k cap) and climbed the prefill ladder
|
||||
> ubatch 512 → 1024 → **2048** — landing **1,005 MiB free** (1,751 at
|
||||
> the 1024 rung; the 2048 rung cost 746 MiB, ~130 over the 616 MiB
|
||||
> measured prediction). This supersedes BOTH earlier 2026-10-05
|
||||
> payloads: the live MiMo-V2.6 Q6_K shape
|
||||
> ([[frank-secondary-llama-mimo-q6k-2x200704]], now retired) and the
|
||||
> Ornith-1.5-9B Q8_0 swap that was committed (77decb5..380aafa) but
|
||||
@@ -93,13 +94,15 @@ field) — the tightest fit in frank-secondary's history, the 2–3 GiB floor
|
||||
knowingly violated, and the 512×512 vision transient (34 MiB) still fits
|
||||
and recovers.
|
||||
|
||||
**The late reshape (2 × 114,688, ubatch 1024) is the current fit.** The
|
||||
per-slot cut frees 2 × 16,384 tokens × 34 KiB ≈ 1.05 GiB of KV; ubatch
|
||||
512 → 1024 spends part of it on compute buffers (a prefill knob — decode
|
||||
never moves with it). Measured boot: **22,374 used / 1,751 MiB free**.
|
||||
The drafter's own KV shrank with its target (draft window 229,376).
|
||||
Compute buffers allocate at graph capture during BOOT, so a miss is loud
|
||||
and fast — the failure mode is a crash loop, not silent corruption.
|
||||
**The late reshape (2 × 114,688, ubatch 2048) is the current fit.** The
|
||||
per-slot cut frees 2 × 16,384 tokens × 34 KiB ≈ 1.05 GiB of KV; the
|
||||
ubatch rungs 512 → 1024 → 2048 spend it back on compute buffers (a
|
||||
prefill knob — decode never moves with it; the rungs cost ~0.3 and
|
||||
~0.75 GiB measured). Measured boot at 2048: **23,120 used / 1,005 MiB
|
||||
free**. The drafter's own KV shrank with its target (draft window
|
||||
229,376). Compute buffers allocate at graph capture during BOOT, so a
|
||||
miss is loud and fast — the failure mode is a crash loop, not silent
|
||||
corruption.
|
||||
|
||||
## Speculative decoding — ON since 2026-10-06 evening (draft-mtp, depth 3)
|
||||
|
||||
@@ -193,7 +196,7 @@ leave room for thinking.
|
||||
slot prefix cache is live.
|
||||
- Deploy: commit da36fa3, e2e gate 33/33 green on the live fleet.
|
||||
|
||||
## Measured: the 2 × 114,688 / ubatch-1024 boot (2026-10-06 late, live)
|
||||
## Measured: the 2 × 114,688 / ubatch-1024 boot (2026-10-06 late, historical)
|
||||
|
||||
- **argv** (from `/proc/<MainPID>/cmdline`): `--ctx-size 229376
|
||||
--parallel 2` (per-slot 114,688), `--batch-size 4096 --ubatch-size
|
||||
@@ -216,6 +219,29 @@ leave room for thinking.
|
||||
`frank-secondary`, config.yml modelRoles rewritten; per-slot
|
||||
`contextWindow: 114688`).
|
||||
|
||||
## Measured: ubatch 2048 (2026-10-06 midnight, live)
|
||||
|
||||
- **argv**: `--ctx-size 229376 --parallel 2 --batch-size 4096
|
||||
--ubatch-size 2048 --spec-type draft-mtp` (commit d8da7a9, Frank's
|
||||
"set ubatch to 2k"; deploy green, e2e gate 33/33).
|
||||
- **VRAM: 23,120 used / 1,005 MiB free at boot** — the 1024 → 2048 rung
|
||||
cost **746 MiB**, ~130 over the 616 MiB the rung measured on
|
||||
2026-10-05 (rung cost is shape-dependent, not a constant). The
|
||||
512×512 solid-red vision probe (`Red`) then took ~240 MiB **and kept
|
||||
it**: settled **763 MiB free** — on this boot the vision encoder's
|
||||
buffers stay resident after the request (the evening boot saw its
|
||||
34 MiB transient return).
|
||||
- **Decode (ubatch-invariant knob, same prompt as the 1024 rung)**:
|
||||
recipe → 52.0 t/s (388/1133, 34.2 %) vs 58.2 t/s / 42.8 % at 1024 —
|
||||
acceptance variance at temp 1.0, not a ubatch effect.
|
||||
- **Prefill (THE ubatch knob)**: **1,209 t/s @ 3,760 tokens** — first
|
||||
recorded number for this shape; future rungs compare against this
|
||||
(no same-prompt 1024 baseline exists; the law predicts ≈ +4.6 %
|
||||
1024 → 2048).
|
||||
- **Headroom left ~0.7–1.0 GiB.** ubatch 4096 (= the logical batch, no
|
||||
micro-splitting) doubles the buffer growth again — not affordable;
|
||||
**2048 is the ceiling for this shape.**
|
||||
|
||||
## Client contract
|
||||
|
||||
- Reasoning in `reasoning_content` (`--reasoning-format deepseek`);
|
||||
@@ -239,9 +265,9 @@ leave room for thinking.
|
||||
|
||||
## Rollback
|
||||
|
||||
**The immediate predecessor shape (2 × 131,072, ubatch 512, same
|
||||
payload) is ONE revert away** — revert f2575a1 and redeploy
|
||||
(`CTX_SIZE=262144`, `UBATCH_SIZE=512`). The 2 × 131,072 no-spec
|
||||
**Predecessor shape (same 2 × 114,688, ubatch 1024) is ONE revert
|
||||
away** — revert d8da7a9 and redeploy. The 2 × 131,072 / ubatch-512
|
||||
era is one revert further (f2575a1). The 2 × 131,072 no-spec
|
||||
IQ3_S-mtp shape is one revert further — revert da36fa3 next: the env
|
||||
trio then ships `SPEC_TYPE=none`, `CTX_SIZE=262144`, `PARALLEL=2`,
|
||||
`UBATCH_SIZE=512` against `/home/dank/models/Swift15-IQ3S/` (the
|
||||
@@ -303,3 +329,10 @@ recipes:
|
||||
frank-small`, then `deploy.sh dankclaw --service frank-secondary`.
|
||||
1,751 MiB free; decode 58.2 t/s recipe / 66.9 temp 0; models.yml +
|
||||
config.yml retargeted.
|
||||
- 2026-10-06 (midnight, Frank): "set ubatch to 2k" → `UBATCH_SIZE=2048`
|
||||
(d8da7a9). Cost 746 MiB: 23,120 used / 1,005 free at boot, settling
|
||||
**763 MiB free after a vision probe** (encoder buffers stay resident
|
||||
on this boot). Decode 52.0 t/s recipe on the shared prompt (58.2 at
|
||||
the 1024 rung — acceptance noise, decode is ubatch-invariant);
|
||||
prefill 1,209 t/s @ 3,760 tokens (first recorded baseline). 2048 is
|
||||
the ceiling for this shape; 4096 would not fit.
|
||||
|
||||
@@ -106,17 +106,19 @@ frank-secondary, port 7771]
|
||||
- [[frank-secondary-llama-swift15-unc-iq3xxs-mtp-114688]] — **ACTIVE since
|
||||
2026-10-05 (evening); UNCECERSED RCO-IQ3_XXS with MTP back on since
|
||||
2026-10-06 evening; RENAMED from frank-small and reshaped to 2 ×
|
||||
114,688 / ubatch 1024 late 2026-10-06** (root systemd unit, port
|
||||
114,688 / ubatch ladder 512 → 1024 → **2048** late 2026-10-06** (root
|
||||
systemd unit, port
|
||||
7771): llama.cpp master
|
||||
(CUDA sm_86) serving ajgazin/Swift-1.5-Qwen3.8-27B-Uncensored-Dynamic-MTP-
|
||||
GGUF **RCO-IQ3_XXS-mtp** (27B; the MTP head in the file is DRAFTED —
|
||||
draft-mtp depth 3, ngram skipped on the recurrent-rollback law) on the
|
||||
RTX 3090, TWO 114,688-token conversations at Frank's 112k cap (pool
|
||||
229376 / parallel 2 — cut from 131,072 to fund ubatch 1024; **1,751
|
||||
MiB measured free**) with
|
||||
229376 / parallel 2 — cut from 131,072 to fund the ubatch rungs;
|
||||
**1,005 MiB free at boot, 763 settled after a vision probe**) with
|
||||
q8_0 K + q8_0 V (FP8 class, 34 KiB/token vs 64 at f16) and
|
||||
vision through the publisher's own mmproj-BF16.gguf. Decode 58.2 t/s
|
||||
recipe / 66.9 temp 0 (MTP acceptance 42.8–54.4 %).
|
||||
vision through the publisher's own mmproj-BF16.gguf. Prefill 1,209
|
||||
t/s @ 3,760; decode ~52–58 t/s recipe (ubatch-invariant; acceptance
|
||||
noise 34–54 %).
|
||||
RCO-IQ3_XXS tier is a per-tensor allocation mix of stock types; the
|
||||
payload is the UNCECERSED Swift 1.5 (23/100 refusals vs Swift 1.5's
|
||||
98/100). Replaces BOTH same-day payloads: the live MiMo Q6_K shape
|
||||
|
||||
Reference in New Issue
Block a user