serverAppConfigs/serverAppConfigs-docs/LLM/frank-medium-llamacpp-dflash2.md

---
type: configuration
title: frank-medium llama.cpp Runbook (DFlash2 drafter)
description: The ACTIVE frank-medium deployment since 2026-09-16 — mainline llama.cpp on Dankserver serving ajgazin/Swift-Qwen3.8-27B-Uncensored-Dynamic-MTP at UD-Q8_K_XL with the z-lab Qwen3.8-27B-DFlash2 Q8_0 drafter, as ONE layer-split process across both Radeon AI PRO R9700 cards at a 36:29 split, a 327680-position KV pool (163840 per conversation over two slots), vision via the BF16 mmproj.
tags:
  - frank-medium
  - dankserver
  - llama-cpp
  - dflash2
  - dspark
  - qwen35
  - gfx1201
  - r9700
  - layer-split
timestamp: 2026-09-17
---

# frank-medium — llama.cpp (DFlash2 drafter)

The ACTIVE frank-medium deployment since 2026-09-16: **mainline llama.cpp**
serving `ajgazin/Swift-Qwen3.8-27B-Uncensored-Dynamic-MTP-GGUF` at `UD-Q8_K_XL`
with the **z-lab DFlash2** block-diffusion drafter, as **one process across both
Radeon AI PRO R9700 cards**, layer-split. DSpark was tried in the drafter's
place for a few hours the same day and reverted — see *The DSpark excursion*.
It replaced the vllm-radiance MXFP4 replica pair + routing proxy
([[frank-medium-radiance-mxfp4]], the record and the PCIe-atomics evidence) in
the same day the pair went live. It is also the box's **only** LLM runtime: the
replicas, the proxy and their unit files are retired.

## Why one process and layer split

The endpoint's whole history is one constraint: **the two cards cannot take
part in an RCCL collective.** RCCL's kernels declare a hidden hostcall buffer,
and ROCr refuses to supply it to a device without PCIe atomics; the second
R9700 hangs off the B650 chipset (`AtomicOpsCap: Routing-`, read-only), so
every collective that touches it dies with `hipErrorIllegalState`. That rules
out tensor parallelism — and it rules out **vLLM's pipeline parallelism too**,
whose stage handoff is a `send`/`recv` of the hidden state on the device
backend (`vllm/distributed/parallel_state.py`), the very primitive that fails.
The full matrix is in [[Dual-R9700-Cooperation]].

llama.cpp's `--split-mode layer` needs **no collective at all**: layers are
distributed across the cards in order and the boundary activation is a plain
per-backend copy, once per forward pass. Measured on this host with the
predecessor runtime (llama-bench, pp4096 / tg128, f16 KV, flash-attn on):

| Split | pp4096 | tg128 |
|---|---:|---:|
| one R9700 (`-sm none`) | 1160.9 | 19.42 |
| **two cards, layer (`-sm layer`)** | **1991.2** | **18.76** |
| two cards, tensor (`-sm tensor`, no RCCL: butterfly fallback) | 271.8 | 26.26 |

Tensor split buys ~40 % decode and loses 7× prefill. The workload here is
prefill-heavy (agentic, long prompts, reasoning traces), so layer split is the
shape — prefill nearly doubles and one model serves from both cards.

## Hardware

| Property | Value |
|---|---|
| GPUs | 2x AMD Radeon AI PRO R9700 (DID 0x7551), gfx1201 (Navi 48, RDNA4) |
| VRAM | 34,208,743,424 B (31.86 GiB) each, as `rocm-smi` reports it |
| Link | PCIe, no XGMI; card #2 behind the chipset, **no atomic routing** |
| iGPU | Raphael (gfx1036) enumerates as HIP device 2 — hidden via `HIP_VISIBLE_DEVICES=0,1` |
| CPU / RAM | Ryzen 7 7700X (8c/16t), 60 GiB RAM, 63 GiB swap |

## Runtime

Mainline llama.cpp at **`fb27a525`** (2026-09-16), built for **gfx1201 only** by
`scripts/build-llama-rdna4.sh` against a private ROCm `7.14.0a20260624`
toolchain (TheRock nightly) that is **bundled next to the binary** —
`RPATH=$ORIGIN/../lib`, no `LD_LIBRARY_PATH`, nothing from the host's ROCm 7.1
packages.

Two features pin that ref, and neither is in the ROCmFPX fork the endpoint used
earlier the same day (its tip, `c49ebdb`, predates both):

- **DFlash2** (`ggml-org/llama.cpp#27342`): grouped dynamic depthwise
  convolution plus the candidate selector, detected from the draft GGUF
  (`selector_top_k > 0`) and served through the ordinary
  `--spec-type draft-dflash` path.
- **qwen35 MTP**: the `draft-mtp` implementation covers this architecture's
  single trained head.

Build with:

```bash
bash scripts/build-llama-rdna4.sh     # ~25 min on this box, JOBS=$(nproc)
```

> **Bundling trap, measured.** rocBLAS and hipBLASLt look for their device code
> at a fixed depth under the binary's lib dir (`../lib/rocblas/library`,
> `../lib/hipblaslt/library/<arch>`). `cp -r SRC DST/` with a missing `DST`
> creates `DST` as a copy of `SRC` and **flattens it one level**, and the
> failure is invisible at startup: the engine loads 29 GiB of weights, answers
> `/health`, and dies on the **first request** with
> `rocBLAS error: Cannot read .../lib/rocblas/library/TensileLibrary.dat: No
> such file or directory for GPU arch : gfx1201`. The build script now declares
> the destination and copies contents.

## Model and drafter

| File | Bytes | Role |
|---|---:|---|
| `Swift-Qwen3.8-27B-Uncensored-Dynamic-MTP-UD-Q8_K_XL.gguf` | 31,457,990,112 | target, 29.29 GiB |
| `Qwen3.8-27B-DFlash2-Q8_0.gguf` | 2,056,414,816 | DFlash2 drafter, 1.92 GiB |

Fetched by `scripts/download-frank-medium-gguf.sh` (resumable, byte-verified —
a truncated 31 GB GGUF is otherwise a load-time crash).

The target is Unsloth Dynamic 3.0 (per-tensor types from Unsloth's own quant of
the same size, on Unsloth's importance matrix) of an abliterated Swift
fine-tune: orcarouter's single refusal direction projected out of 131 tensors,
vision tower untouched. **Text only here** (`--no-mmproj`); the fleet's image
endpoint is frank-small.

**The file also carries the model's MTP head** (`blk.64.nextn.*`). Under
`--spec-type draft-dflash` those tensors are deliberately **not** loaded — the
log says `model has unused tensor blk.64.nextn.eh_proj.weight ... ignoring` —
because DFlash2 drafts from its own 5-layer sidecar. Switching (or chaining)
`--spec-type draft-mtp,draft-dflash` is a one-line env change that pulls the
head in; it is not enabled because the DFlash2 path is the measured one (below)
and because a chain cannot hold two context-backed drafters at all.

## Deployment

| File | Role |
|---|---|
| `scripts/frank-medium.env` | every tunable, with the sizing arithmetic in comments |
| `scripts/serve-frank-medium.sh` | env-driven llama-server launcher; no arguments |
| `scripts/frank-medium.service` | ROOT systemd unit, `User=dank`, `WantedBy=multi-user.target` |

```bash
./scripts/deploy.sh dankserver --service frank-medium
```

The handler verifies the runtime and payload exist (and refuses otherwise),
retires the three vLLM quadlets into `~/.AGENTTRASH/20260916-vllm-radiance-retire/`,
waits for **port 7770 to be released** (the retired proxy held it on the host
network), relinks and restarts the unit, and gates on
`http://127.0.0.1:7770/health`.

Deployed flags:

| Flag | Value | Why |
|---|---|---|
| `--split-mode` / `--device` / `--tensor-split` | `layer` / `ROCm0,ROCm1` / `36,29` | both cards, one model, no collective; the split is skewed because ROCm1 carries the drafter, and it is one LAYER of granularity — 0.43 GiB on a DeltaNet boundary, 1.43 GiB on an attention one. Since 2026-09-17 it is one layer PAST the balance point at the 327680 pool, on purpose: the move bought headroom on the drafter card (see below) |
| `--gpu-layers` / `--fit` | `999` / `off` | everything on the cards; auto-fit must not resize a context we set |
| `--ctx-size` / `--parallel` | `327680` / `2` | the pool over two slots of 163840; `--parallel` **divides** the context. 1.25x the trained 262144 window, and the GGUF has no rope scaling — see the 2026-09-17 section |
| `--batch-size` / `--ubatch-size` | `6144` / `512` | measured: ubatch 512 is the prefill optimum *and* the cheapest point on the curve; the logical batch is throughput- and VRAM-neutral. See [[frank-medium-batch-ubatch]] |
| `--ctx-checkpoints` / `--cache-ram` | `0` / `8192` | no per-slot KV snapshots (the build's default); the RAM-side prompt cache is capped at 8 GiB |
| `--flash-attn` / cache types | `on` / `f16` K and V | an agentic checkpoint is the wrong place to spend KV precision |
| `--spec-type` / `--spec-draft-n-max` | `draft-dflash,ngram-mod` / `7` | DFlash2 blocks are 8 tokens, so 7 drafts is the ceiling; ngram-mod rides the chain as a draftless second proposer |
| `--spec-draft-device` | `ROCm1` | the drafter rides the card that ends up holding the target's last layers |
| `--temp` / `--top-p` / `--top-k` | `0.7` / `0.95` / `20` | the values the vLLM predecessor served on this endpoint |
| `--reasoning-format` / `--reasoning-budget` | `deepseek` / `-1` | trace into `reasoning_content`, unlimited |
| `--mmproj` | `mmproj-BF16.gguf` (888 MiB, beside the target) | vision enabled since 2026-09-17; this build has NO autoload, so the flag is explicit and the serve script refuses to start without the file |

## The DSpark excursion (2026-09-16, tried and reverted)

The endpoint went live on **z-lab DFlash2**, was switched to
**magnitudedev/Qwen3.8-27B-DSpark** for a few hours the same day, and was put
back. Both are 5-layer block-diffusion sidecars, and their differences are what
decided it:

| | DFlash2 (deployed) | DSpark (tried, reverted) |
|---|---|---|
| file | 2,056,414,816 B — 1.92 GiB | 1,455,376,576 B — 1.36 GiB |
| draft depth | `block_size 8` -> `n_max 7` | `block_size 7` -> `n_max 6` (llama.cpp asserts `n_max <= block_size - 1`) |
| attention | `sliding_window 2048`, `causal false`, candidate selector (rank 256, top-k 16) | **no sliding window**; a Markov head in place of the selector |
| draft KV at 262144 | ~40 MiB — the window bounds it | **5.0 GiB** — the whole context |

> **A fetch-script bug this threw up.** The DSpark file's size was recorded as
> 1,359,284,737 when it was fetched — 96 MB short of the Hub's 1,455,376,576 —
> and that wrong number became the fetch script's declared size, so
> `--verify-only` failed on a payload that was in fact byte-correct. Both
> drafters' sha256 have since been checked against the Hub's LFS oids and match.

**The draft context is sized from the target's.** `cparams.n_ctx =
llama_n_ctx(ctx_tgt)` in `common/speculative.cpp`, with no flag to cap it
independently, so a drafter that declares no sliding window caches the entire
target window on whichever device `--spec-draft-device` names. DSpark's KV is
5 layers x 2 x 8 kv heads x 128 dim x 2 B = 20 KiB per position.

That cost has to be paid somewhere, and the failure was instructive: at a 1:1
split the model **loaded fine, answered `/health`, and then died on the first
draft decode** with `ROCm error: out of memory` inside
`common_speculative_impl_draft_dflash::process` — ROCm1 sat at 33.9 GB of
34.2 GB. A unit that crash-loops with an allocation failure *after* a
successful load is a sizing failure, not a broken drafter.

Read `sliding_window` out of a drafter's GGUF header before sizing a
spec-decode deployment — 40 lines of `struct` parsing is enough, and the
flag-level configuration looks identical either way.

### The split moved twice: once for the batch, once for the drafter

**Under DSpark.** Tripling the batch (2048/512 -> 6144/1536) made the two cards
diverge: at 262144 the bigger `--ubatch-size` cost **ROCm1 ~3.3 GiB against
ROCm0's ~1.7 GiB** — ROCm1 holds the output layers *and* the drafter's graphs —
which left the draft-carrying card at 0.08 GiB free against ROCm0's 3.78 under
the 38:27 split that had been balanced at the smaller batch:

| `-ts` | GPU 0 free | GPU 1 free |
|---|---:|---:|
| 38,27 | 3.78 GiB | 0.08 GiB |
| 41,24 | 1.47 GiB | 2.38 GiB |
| 40,25 | 1.88 GiB | 1.88 GiB |

**Then DSpark came off**, which frees ~4.3 GiB on ROCm1 (5.0 GiB of draft KV
out, 0.65 GiB of heavier DFlash2 weights in) and moves the balance the other
way. Re-measured at the same batch, the same two slots and the same window:

| `-ts` | GPU 0 free | GPU 1 free | gap |
|---|---:|---:|---:|
| 39,26 | 2.42 GiB | 7.20 GiB | 4.78 |
| 38,27 | 3.85 GiB | 5.77 GiB | 1.92 |
| 37,28 | 4.28 GiB | 5.34 GiB | 1.06 |
| **36,29 — deployed** | **4.71 GiB** | **4.91 GiB** | **0.20** |
| 35,30 | 5.14 GiB | 4.48 GiB | 0.66 |
| 34,31 | 6.57 GiB | 3.05 GiB | 3.52 |

**One `-ts` step is one layer, and this stack's layers are not the same size.**
qwen35 is 16 x (3 Gated DeltaNet + 1 Gated Attention), so a step is worth
**~0.43 GiB** on a DeltaNet boundary and **~1.43 GiB** on a full-attention one
(0.45 GiB of weights plus ~1.0 GiB of its own f16 KV at 262144). Both fell out
of that table — 37,28 -> 38,27 moves a DeltaNet layer, 38,27 -> 39,26 an
attention layer. Balance by measurement, never by interpolating.

**Then the batch moved, and the split followed it** (2026-09-16, the same day
— see [[frank-medium-batch-ubatch]]). 36:29 was the balance at ubatch **1536**;
the sweep showed 512 is both faster and 3.71 GiB cheaper, and — because the
compute buffers cost ROCm1 nearly twice what they cost ROCm0 — shrinking them
handed ROCm1 1.31 GiB more than it handed ROCm0:

| `-ts` | ubatch | GPU 0 free | GPU 1 free | gap |
|---|---:|---:|---:|---:|
| 36,29 | 1536 | 4.71 GiB | 4.91 GiB | 0.20 |
| 36,29 | 512 | 6.01 GiB | 7.32 GiB | 1.31 |
| **35,30 — deployed** | **512** | **6.44 GiB** | **6.90 GiB** | **0.46** |

35:30's 0.46 GiB gap is one DeltaNet layer's worth, which is the floor here: no
split can be tuned finer than a layer, so the 0.20 GiB of the old configuration
is not reachable at this batch. It clears the operator's 1.5 GiB-per-card floor
by ~5 GiB, so no headroom is bought out of `CTX_SIZE` and the model's full
262144-token window stays.

A batch of 8192/2048 failed here under DSpark — its 2020 MiB pp buffer could not
be allocated on ROCm1, which had 0.08 GiB free. That was a *contiguity* failure,
not a total-bytes one, and the sweep has since removed the reason to care: with
the batch geometry measured, there is nothing to gain by making either knob
larger, so the question is closed rather than pending.

> **A fault to watch.** A 39:26 split, at 1x batch and one slot, died on its
> eighth request: the amdgpu driver logged SDMA0 UTCL2 page faults and the
> engine surfaced `ROCm error: an illegal memory access was encountered` ->
> `ggml_abort` — a fault in the cross-card boundary copy, which is this layer
> split's hot path. It has not reproduced (36:29 served the whole verification
> battery and the e2e gate, and 35:30 at ubatch 512 is the deployed shape now;
> 39:26 itself was only *loaded* at the deployed batch, not exercised), and it
> is **not** an OOM: no amount of headroom would prevent it.

## 2026-09-17: the pool grows to 327680, the split moves to 36:29, vision comes on

The window grew from 262144 to a **327680-position pool** (163840 per
conversation over the two slots), the split moved one layer to ROCm0
(35:30 → 36:29), and the **BF16 mmproj** (888 MiB) came on.

**Why 36:29, not the balance.** At this context the fit model puts the balance
point at 34:31 (0.11 GiB gap). The operator moved a layer to ROCm0 to buy
headroom on ROCm1 — the card that carries the drafter, its KV, the output
layers and the heavier compute buffers — accepting a 3.15 GiB gap by
construction:

| Card | Fit | Measured at load | Headroom |
|---|---:|---:|---:|
| ROCm0 (36 layers + mmproj) | 29.19 GiB | 28.40 GiB | 3.46 GiB |
| ROCm1 (29 layers + drafter) | 26.04 GiB | 26.66 GiB | 5.20 GiB |

Both clear the 1.5 GiB floor with room; the fit lands within 0.8 GiB on both
cards, which is the accuracy it has always had (at the 35:30 point it
reproduced ROCm1 to 0.00 and ROCm0 to 0.86). The seam's slack is the 3.15 GiB
gap rounded up, with the trade written in its comment.

**The rope caveat.** The GGUF carries no `context_length` and no rope-scaling
keys (freq_base 1e7, `dimension_sections [11,11,10,0]`); the checkpoint's
trained window is 262144. Positions beyond that — the top 65k of the pool —
extrapolate on the base rope. It runs, and 1.25x is a modest ask of a rope,
but it is untrained territory, and the seam's ctx cap encodes 327680 with
that note.

**Vision: this build has no mmproj autoload.** The first 327680/36:29 deploy
came up healthy and *text-only*: image requests answered 500 "image input is
not supported — hint: … provide the mmproj" and the load log had no mmproj
line, so `llama-server` fb27a525 does not pick up `mmproj*.gguf` from the
model directory. The serve script now passes `--mmproj` explicitly (the
frank-small pattern), refuses to start without the file when vision is on, and
the deploy handler's preflight checks for it. Verified end-to-end after the
fix: a generated 64x32 test image was described from its pixels — with
thinking on the model reasoned about "the three horizontal bars" (its reading
of the crude glyph) and with thinking off answered the letter question in one
token.

The e2e crawl spec flaked once on the first 327680 deploy (1 failed / 31
passed) and passed 32/32 on the redeploy; the service itself was healthy
throughout (health gate green, `NRestarts=0`).

## Verified serving behaviour (2026-09-16)

- Load: `model loaded` ~25 s after start with a warm page cache, then
  `listening on http://0.0.0.0:7770`. The drafter adds ~2.5 s.
- Slot shape: `n_slots = 2, n_ctx_slot = 131072`; `/props` reports
  `modalities: {vision: false}` and the sampler defaults above.
- DFlash2 engaged — the init lines are the proof, not the flags:

  ```
  common_speculative_init_result: loading draft model '/home/dank/models/Qwen3.8-27B-DFlash2-GGUF/Qwen3.8-27B-DFlash2-Q8_0.gguf'
  common_speculative_impl_draft_dflash: adding speculative implementation 'draft-dflash'
  common_speculative_impl_draft_dflash: - n_max=7, n_min=0, p_min=0.00
  common_speculative_impl_draft_dflash: - block_size=8, mask_token_id=248070, n_extract=5, sample_from_anchor=true
  ```

  `block_size=8` and `n_extract=5` are DFlash2's own metadata; the candidate
  selector is what distinguishes it from DFlash 1. DSpark logs under the same
  `draft_dflash` symbol with `block_size=7` and a Markov head, so read the
  numbers, not the implementation name.
- Both cards hold the model and they are **balanced**: at 262144 with the
  deployed batch and split, `rocm-smi` reports **6.44 GiB free on GPU 0 and
  6.90 GiB on GPU 1** of 31.86 GiB each — reproducing the pre-deploy
  measurement of the same shape to 0.01 GiB. That is the reading straight after
  load; once the service has served traffic it settles ~0.2 GiB lower
  (**6.23 / 6.64**, the same with two concurrent requests in flight and after
  them). Both figures are ~5 GiB above the operator's 1.5 GiB floor.
- Drafting is live on **both slots**, which is what a 2-slot deployment has to
  prove: `slot print_timing` reported `draft acceptance = 0.62857 (44 accepted /
  70 generated), mean len = 5.40` and `0.48214 (27 / 56)` on slot 1, and
  `0.38776 (57 / 147), mean len = 3.71` on slot 0, from one concurrent pair.
  Acceptance moves with the text; the point is that neither slot is idle.
- **140,069 prompt tokens prefilled in 134 s** (1043 tok/s) was measured
  through a *single* slot, at the previous configuration: the raised window is
  real rather than declared, and it is 22 % beyond the 114688 the vLLM
  predecessor could offer. The window is now split over two slots.

- **Nothing is replicated.** The loader does not print a per-device ledger at
  this verbosity, so this is measured instead of read: raising CTX_SIZE from
  131072 to 262144 added **4.83 GB to GPU 0 and 4.84 GB to GPU 1** — both cards
  carry the KV for their own attention layers, about half each — and neither
  card's *total* usage (24.94 / 29.42 GB at 262144) could hold the 31.46 GB
  file, so no card carries a full copy of the weights. Compare the shape this
  replaced: two vLLM replicas, i.e. two complete copies of the model, one per
  card, which is exactly why a 29.8 GB FP8 checkpoint could not be served there
  at any usable context.

### Measured throughput (2026-09-16, deployed service, `temperature 0`)

Same filler corpus for every shape, so these are shapes rather than a
benchmark: a large prompt with a tiny budget isolates prefill, a small prompt
with a long budget isolates decode. `draft`/`acc` are per request; acceptance
moves with the text (filler prose accepts far worse than code or a real agent
loop).

| Shape | Prefill | Decode | Acceptance |
|---|---|---|---|
| 4k prompt / 32 out | 3994 tok in 3.25 s — 1230 tok/s | 59.8 tok/s | 71 % |
| 1k prompt / 512 out | 998 tok in 1.41 s — 707 tok/s | **43.8 tok/s** | 41 % |
| 16k prompt / 16 out | 12,528 tok in 8.94 s — **1402 tok/s** | — | 100 % (13/13) |
| 64k prompt / 16 out | 48,508 tok in 39.8 s — 1219 tok/s | — | 53 % |
| 140k prompt / 16 out | 140,069 tok in 134.3 s — 1043 tok/s | — | — |
| same 1k prompt again | **4 tokens prefilled** | 43.8 tok/s | 41 % |

The last row is the prefix cache doing its job: the second request of the same
conversation re-prefilled 4 of 998 tokens. Prefill holds ~1.0-1.4k tok/s from
4k to 140k, and decode sits at ~44 tok/s on a long generation — against the
vLLM predecessor's 42.8 tok/s single-stream (two replicas) and the ROCmFPX
llama.cpp measured here at 35.7-46.2 tok/s. One process, one model, both cards,
no proxy.

### What the drafter is worth — and why MTP is not the alternative

Measured 2026-09-16 with `scripts/bench-spec-ab.py` on the **DFlash2** drafter —
the one deployed now: four configurations of the same binary, identical prompts
at `temperature 0`, unit stopped between runs (one host, one copy of a 29 GiB
model). 1k-token prompt, 512-token budget. These are the numbers that selected a
trained multi-token drafter over the model's own MTP head.

| Configuration | Decode | Drafting | VRAM (card 1) |
|---|---:|---|---:|
| `none` — autoregressive | 17.7 tok/s | — | 26.07 GB |
| `draft-mtp` n_max 3 (the model's own head) | 32.4 tok/s | 58 % of 72 | 29.35 GB |
| `draft-mtp` n_max 7 | 26.7 tok/s | 33 % of 147 | 29.65 GB |
| **`draft-dflash` n_max 7 — deployed** | **43.5 tok/s** | 41 % of 119 | 29.42 GB |

- **DFlash2 is worth 2.46× over autoregressive and 34 % over the best MTP.**
  Deeper MTP drafting costs more than it returns: at depth 7 only a third of
  the proposals survive, at depth 3 more than half do.
- **All four produced identical greedy text** (`2, 3, 5, 7, 11`): speculation
  buys speed, never a different answer. The harness warns loudly if a future
  configuration ever breaks that.
- **MTP is not the cheaper option.** Selecting it loads `blk.64.nextn.*` from
  the target and adds ~3.3 GB to the card that holds it, against 2.06 GB for
  the drafter's file — which is also why the load log says
  `unused tensor blk.64.nextn... ignoring` under `draft-dflash`: correct
  behaviour, not a truncated download.
- **They cannot be chained.** `--spec-type draft-mtp,draft-dflash` dies at load
  with `context type MTP requested but model doesn't contain MTP layers`. A
  chain has ONE draft context, and MTP builds against whatever model that
  context holds — here the DFlash2 file. MTP's head is loaded only when MTP *is*
  the draft model (`creating MTP draft context against the target model ...`).
  That is structural, not a tuning question.

### Chaining the draftless n-gram matcher (deployed)

`ngram-mod` **can** ride beside a context-backed drafter, and it is enabled.
The reason is in `common/speculative.cpp`: the n-gram types are added to the config vector
unconditionally while every model-backed drafter is gated on
`ctx_dft != nullptr` — so n-gram needs no draft context and cannot collide with
the drafter over one. (MTP is the opposite: it *is* context-backed, which is why
`draft-mtp,draft-dflash` cannot load.) The vector's fixed order — ngram types
first, then the drafters — also means CLI order is irrelevant.

The measurements below are DFlash2's — the deployed configuration. (During the
DSpark excursion the chain was `draft-dspark,ngram-mod`; the matcher's behaviour
is a property of the matcher, not of the drafter beside it.)

Measured with `scripts/bench-spec-ab.py`, decode tok/s, three shapes that a
proposer can and cannot match:

| Configuration | prose 1k/512 | echo 1.5k/400 (copy 0.94) | structured/400 | identity |
|---|---:|---:|---:|---:|
| `draft-dflash@7` | 43.77 | 76.82 | 91.08 | 70.37 |
| `ngram-mod` alone | 17.72 *(0 drafts)* | 102.50 | 17.80 *(0 drafts)* | 17.77 |
| **`draft-dflash,ngram-mod@7`** | **43.65** | **200.58** | 91.22 | 70.40 |

- **On prompt-echo traffic the chain is 2.6× the drafter alone** (200.6 vs 76.8)
  and twice `ngram-mod` by itself, at 100 % acceptance.
- **On prose it is indistinguishable from DFlash2 alone** — the same 119 drafts
  and 49 accepts, the same 43.7 tok/s. That is the property that makes it safe
  as a default: where the matcher cannot match, it costs nothing.
- `ngram-mod` alone is a *negative control*: zero drafts on prose and identity
  (17.7 tok/s = the autoregressive baseline), 100 % acceptance on echo. Nothing
  else could have proposed those tokens, which is how its drafts are identified
  at all — see the trap below.
- VRAM is unchanged (29.42 GB on card 1 with or without it): the matcher is a
  64 MiB host-RAM hash table.
- `structured` (25 records with unique ids) rewards no proposer: its lines
  differ, so there is no long span to match. It is a negative control for
  *self-repetition*, not evidence about it.

**The window matters, and shorter is not better.** The chain at three windows:

| `SPEC_NGRAM_N_MIN`/`N_MAX` | prose 1k/512 | echo 1.5k/400 |
|---|---:|---:|
| **48/64 — deployed** | **43.9** | **200.6** |
| 16/32 | 36.0 | 161.0 |
| 8/16 | 36.2 | 113.8 |

A short window makes the matcher propose on ordinary prose fragments, where the
proposals are rejected and the verification is still paid — the "ngram hurts"
result this fleet measured twice before on other payloads. At 48/64 the chain
keeps DFlash2's exact numbers on prose and wins on echo.

> **Operational trap: `ngram-mod` prints no startup banner in this build.**
> `journalctl -u frank-medium` shows `adding speculative implementation
> 'draft-dflash'` and nothing for the matcher — the only evidence it is running
> is behavioural (`draft_n` > 0 where text repeats) or the per-task line
> `slot print_timing: ... draft acceptance = 1.00000 (256 accepted / 256
> generated), mean len = 65.00`. Do not conclude from the load log that the
> chain is not engaged.

### The agent-loop shape (fleet harness, 2 families × 2 turns)

`scripts/bench-turn-latency.py http://127.0.0.1:7770 2 2 LAYERSPLIT` — two
agent loops re-sending a ~30k-token document concurrently:

| | turn 1 | turn 2 |
|---|---:|---:|
| family 1 | 24,799 ms | 30,697 ms |
| family 0 | 51,424 ms | 8,015 ms |

Read that against the prefill table, not as a latency regression: with **one**
slot the second family's first turn waited for the first (25 s of cold 30k
prefill + the wait ≈ 51 s), and the last number — 8.0 s — was a re-prefill the
cache could only partly serve. That was the 1-slot configuration. The
deployment now runs **two slots of 131072**, so a second agent loop has a slot
of its own instead of queueing, at the cost of halving the window each one
gets. `--parallel` splits the context and the KV between slots; it does not add
throughput, so the trade is concurrency against conversation length.

### Benchmarking this endpoint

`scripts/bench-batch-ubatch.sh` sweeps `--batch-size` against `--ubatch-size`
with `llama-bench` and records, per cell, the prefill rate, the decode rate and
each card's **peak** VRAM. Run it from a transient unit rather than a shell:

```bash
sudo systemd-run --unit=fm-bench --collect --no-block --property=Type=oneshot \
     --property=LimitMEMLOCK=infinity --property=User=dank \
     scripts/bench-batch-ubatch.sh
```

Properties of `llama-bench` shape that harness, and three of them have already
produced wrong numbers on this fleet:

- **It separates devices differently from `llama-server`.** `/` splits devices
  *within one configuration*, `,` splits *sweep values* — so this service's
  `--tensor-split 36,29` is `-ts 36/29` to llama-bench, and the comma form
  silently benches each card on its own instead. Likewise `--device
  ROCm0,ROCm1` → `-dev ROCm0/ROCm1`.
- **There is no `-c`.** The context is a consequence of the test shape:
  `n_ctx = n_prompt + n_gen + n_depth`. No bench can therefore prove that a
  configuration's activation buffers fit beside the *deployed* KV — that needs
  the live unit at 327680 across two slots.
- **A test that cannot allocate calls `exit(1)`**, taking the whole process with
  it, so the harness runs one invocation per cell and a failure costs one TSV
  line instead of the rest of the sweep.
- **A shell's memlock limit is not the unit's.** The unit sets
  `LimitMEMLOCK=infinity` for the ROCm staging buffers; an SSH shell here gets
  8 MiB, which fails the load for a reason that has nothing to do with the
  model being benched.
- **No `--spec-*` and no `--parallel`.** The drafter cannot take part, so a
  `llama-bench` decode figure is the *drafterless* baseline — 15.9 tok/s at 64k
  depth against the deployed 43.8 — and slots are never exercised. `-d <n>` is
  what puts KV in front of the measurement at all: a `tg` instance runs with
  `n_prompt = 0`, i.e. at ~zero depth unless `-d` says otherwise.

## Observability

The endpoint exports Prometheus metrics under the **`llamacpp:`** namespace
(`--metrics`), which is what the fleet's scrape and dashboard read — the
`vllm:` series the predecessor exported no longer exist:

| Need | Series |
|---|---|
| Throughput | `llamacpp:prompt_tokens_seconds`, `llamacpp:predicted_tokens_seconds` |
| Queue | `llamacpp:requests_processing`, `llamacpp:requests_deferred` |
| Cache reuse | `llamacpp:prompt_tokens_cached_total` vs `llamacpp:prompt_tokens_total` |
| **Speculative decoding is live** | `llamacpp:spec_decode_num_drafts_total` and `llamacpp:spec_decode_num_accepted_tokens_total` (their ratio is the acceptance rate) |

`spec_decode_num_drafts_total` staying at 0 is the one-line answer to "is the
drafter actually running": the flags can all be right while the draft model
failed to load.

## Client contract

OpenAI-compatible `/v1` on **7770**, alias **`frank-medium`**, streaming and
`/health`, `/props`, `/metrics` as llama.cpp provides them. Reasoning traces
are projected into `reasoning_content`. A request that sends no sampler fields
gets the server defaults above; a client that sends its own wins. Text only.

## Troubleshooting

- **Loads, then dies on the first request with a rocBLAS Tensile error** — the
  bundled device-library depth (see the bundling trap above); check
  `build-rdna4-rocm714/lib/rocblas/library/` exists and is populated.
- **`hipErrorNoDevice` / a card missing** — `HIP_VISIBLE_DEVICES` must be
  `0,1`; the iGPU enumerates as device 2 and must stay hidden.
- **Drafting not engaged** — read the journal for
  `common_speculative_impl_draft_dflash` (DFlash2 and DSpark both log under that
  symbol); a missing drafter file makes the serve script exit before
  llama-server starts, and a drafter whose GGUF the build does not recognise
  fails the load instead.
- **Why is `blk.64.*` "unused"?** That is the model's own MTP head and it is
  correct for `draft-dflash`. It is not a truncated download:
  `bash scripts/download-frank-medium-gguf.sh --verify-only` proves the bytes.
- **A rebuild segfaults at load** — the build is gfx1201-only on purpose; a
  gfx1200 sibling binary links, loads the model and then segfaults on these
  cards.

## See Also

- [[frank-medium-radiance-mxfp4]] — the retired vllm-radiance MXFP4 deployment
  (replicas + proxy) and the PCIe-atomics evidence
- [[frank-medium-rocmfpx]] — the llama.cpp/ROCmFPX deployment earlier on
  2026-09-15, whose `--split-mode layer` measurements this service reuses
- [[Dual-R9700-Cooperation]] — why the two cards cannot take part in a
  collective, and every software escape that is closed
- [[frank-small-qwen38-gsq-rco]] — the fleet's other llama.cpp endpoint (RTX
  3090, MTP, the image path)
- [[Dankserver System Specs]] — hardware inventory
- [[frank-medium-batch-ubatch]] — the batch/ubatch sweep that set the deployed
  geometry and moved this split from 36:29 to 35:30: the ubatch optimum at 512,
  why the logical batch is free, and the harness traps