Frank
a4f4429a99
ngram-mod is draftless (added to the spec config vector unconditionally, while every model-backed drafter needs ctx_dft), so unlike MTP it can share the process with DFlash2. Chained at the fleet's 48/64 window, over three shapes: prose 1k/512 dflash 43.77 | ngram 17.72 (0 drafts) | chain 43.65 echo 1.5k/400 dflash 76.82 | ngram 102.50 | chain 200.58 structured/400 dflash 91.08 | ngram 17.80 (0 drafts) | chain 91.22 identity dflash 70.37 | ngram 17.77 | chain 70.40 On prose the chain is byte-identical to the drafter alone (same 119 drafts/49 accepts) -- that is what makes it a safe default -- and on prompt-echo traffic it is 2.6x. VRAM is unchanged: the matcher is a 64 MiB host-RAM hash table. The window sweep says keep the long one: 48/64 beats 16/32 (161.0) and 8/16 (113.8) on echo, and shortening it costs prose (43.9 -> 36.0) because the matcher then proposes on ordinary fragments and the rejections still have to be verified. That is the 'ngram hurts' result this fleet hit twice before. Two documentation traps recorded with it: ngram-mod prints NO startup banner in this build (its drafts are only visible behaviourally), and the harness's 'structured' shape is a negative control because its lines differ.
211 lines
10 KiB
Bash
211 lines
10 KiB
Bash
# Tunables for frank-medium (ajgazin/Swift-Qwen3.8-27B-Uncensored-Dynamic-MTP
|
|
# UD-Q8_K_XL + z-lab/Qwen3.8-27B-DFlash2-GGUF Q8_0 drafter), mainline llama.cpp
|
|
# on Dankserver, 2x AMD Radeon AI PRO R9700 (gfx1201). Since 2026-09-16 this
|
|
# is the SOLE LLM runtime on the box: the vllm-radiance replica pair and its
|
|
# routing proxy are retired.
|
|
#
|
|
# Hardware: two R9700 (Navi 48, RDNA4, 32,624 MiB each), no XGMI, different
|
|
# IOMMU groups -- every cross-card byte goes over PCIe. The Raphael iGPU
|
|
# (gfx1036/Radeon 610M) enumerates as HIP device 2 and is hidden below so
|
|
# nothing can drift onto shared system RAM.
|
|
#
|
|
# WHY LAYER SPLIT AND NOT TENSOR (operator call, 2026-09-16): tensor parallel
|
|
# needs a cross-card allreduce per layer, and this host cannot dispatch one.
|
|
# RCCL's kernels carry a hidden hostcall-buffer parameter, and ROCr refuses it
|
|
# on a device without PCIe atomics -- the second card sits behind the B650
|
|
# chipset bridges (AtomicOpsCap: Routing-, read-only), so every collective that
|
|
# touches it dies with hipErrorIllegalState. Measured on this box 2026-09-15
|
|
# (llama-bench, pp4096 / tg128, f16 KV, fa on):
|
|
#
|
|
# single R9700 1160.9 / 19.42
|
|
# layer 2x 1991.2 / 18.76 (859.1 / 17.64 at depth 32768)
|
|
# tensor 2x 271.8 / 26.26 (no RCCL: butterfly fallback, -7x prefill)
|
|
#
|
|
# Layer split distributes layers in order; only the activation at the boundary
|
|
# crosses the wire, once per forward pass. That is the "pipeline parallelism"
|
|
# this service wanted, and it needs no collective at all.
|
|
#
|
|
# Runtime: mainline llama.cpp master fb27a525 (2026-09-16), gfx1201, built by
|
|
# scripts/build-llama-rdna4.sh against a private ROCm 7.14.0a20260624 toolchain
|
|
# that is bundled next to the binary (RPATH $ORIGIN/../lib, no LD_LIBRARY_PATH).
|
|
# The ref is pinned by TWO features: DFlash2 (ggml-org/llama.cpp#27342 -- the
|
|
# drafter is detected from its GGUF) and qwen35 MTP. Do not float it.
|
|
#
|
|
# Model: ajgazin/Swift-Qwen3.8-27B-Uncensored-Dynamic-MTP-GGUF @ UD-Q8_K_XL,
|
|
# 29.29 GiB, arch qwen35, Unsloth Dynamic 3.0 (per-tensor types from Unsloth's
|
|
# own quant of the same size, on Unsloth's importance matrix). Abliteration is
|
|
# orcarouter's single refusal direction projected out of 131 tensors; the vision
|
|
# tower is untouched but unused here (text only, see NO_MMPROJ). The file also
|
|
# carries the model's MTP head (blk.64.nextn.*), so a file-level switch to
|
|
# --spec-type draft-mtp is available without a second copy in VRAM.
|
|
#
|
|
# Drafter: z-lab/Qwen3.8-27B-DFlash2-GGUF @ Q8_0, 1.92 GiB: 5 layers, hidden
|
|
# 5120, block-diffusion proposal with the candidate selector. Decoding stays
|
|
# lossless -- the target verifies every drafted token.
|
|
#
|
|
# Architecture (GGUF arch qwen35): 64 layers as 16 x (3 x (Gated DeltaNet ->
|
|
# FFN) + 1 x (Gated Attention -> FFN)) -- 48 linear-attention layers whose
|
|
# per-sequence state is CONSTANT-SIZE, 16 full-attention layers at 4 KV heads x
|
|
# 256 head_dim. A token therefore costs 2 x 4 x 256 x 2 B = 64 KiB of KV at f16
|
|
# in the attention layers only, plus ~0.16 GiB per sequence of f32 DeltaNet
|
|
# state at any depth.
|
|
#
|
|
# SIZING, measured (rocm-smi, 2026-09-16). Weights split across the two cards;
|
|
# the drafter rides the second. The loader's compute buffers are part of what
|
|
# is seen below -- they are allocated at load, not per request:
|
|
#
|
|
# CTX_SIZE GPU 0 GPU 1 headroom on the busier card
|
|
# 131072 19.89 GB 24.30 GB 9.9 GB / 31 %
|
|
# 262144 24.72 GB 29.14 GB 5.07 GB / 15 % <- deployed
|
|
#
|
|
# 262144 is the window the model ships (n_ctx_train) and it fits with room, so
|
|
# the fleet gets the whole thing; the arithmetic that used to cap this endpoint
|
|
# at 114688 was the vLLM predecessor's, not this runtime's. If a future change
|
|
# adds VRAM (a longer drafter, quantized KV, more slots) re-read the numbers
|
|
# rather than assuming, and prefer CTX_SIZE over --gpu-layers.
|
|
#
|
|
# WARNING: do not name any variable TEMP, HOST, or GPU_MAX_HEAP_SIZE (HIP reads
|
|
# those bare vars; 2026-08-13 incident). llama.cpp takes --host/--port/--temp
|
|
# as flags only.
|
|
|
|
# llama-server: mainline fb27a525 built for gfx1201 by scripts/build-llama-rdna4.sh.
|
|
LLAMA_BIN=/home/dank/GitPackages/llama.cpp-dflash2/build-rdna4-rocm714/bin/llama-server
|
|
|
|
# Payload, fetched with scripts/download-frank-medium-gguf.sh.
|
|
MODEL_DIR=/home/dank/models/Swift-Qwen3.8-27B-Uncensored-Dynamic-MTP-GGUF
|
|
MODEL_FILE=Swift-Qwen3.8-27B-Uncensored-Dynamic-MTP-UD-Q8_K_XL.gguf
|
|
DRAFT_MODEL_DIR=/home/dank/models/Qwen3.8-27B-DFlash2-GGUF
|
|
DRAFT_MODEL_FILE=Qwen3.8-27B-DFlash2-Q8_0.gguf
|
|
|
|
# Fleet identity. 7770 is the fleet's dankserver endpoint; the alias is the id
|
|
# at /v1/models and what every client asks for.
|
|
ALIAS=frank-medium
|
|
BIND_ADDR=0.0.0.0
|
|
LISTEN_PORT=7770
|
|
# Device placement. HIP_VISIBLE_DEVICES hides the Raphael iGPU (HIP device 2)
|
|
# so nothing can drift onto shared system RAM; DEVICES is what llama.cpp splits
|
|
# across, and neither of the two cards has an XGMI link to the other.
|
|
HIP_VISIBLE_DEVICES=0,1
|
|
DEVICES=ROCm0,ROCm1
|
|
SPLIT_MODE=layer
|
|
# Empty = distribute layers by free VRAM (equal here, so 1,1 by hand).
|
|
TENSOR_SPLIT=1,1
|
|
|
|
NGL=999
|
|
# Auto-fit has no business resizing a context we set explicitly.
|
|
FIT=off
|
|
FLASH_ATTN=on
|
|
|
|
# One slot at the model's full configured window (n_ctx_train 262144), which was
|
|
# measured to fit before it was deployed: see SIZING above. --parallel DIVIDES
|
|
# --ctx-size between slots, so one slot carries the whole window and a second
|
|
# concurrent request queues behind it.
|
|
CTX_SIZE=262144
|
|
PARALLEL=1
|
|
|
|
BATCH_SIZE=2048
|
|
UBATCH_SIZE=512
|
|
|
|
# Threads cover tokenization, sampling and HTTP only: every layer is on a GPU.
|
|
NUM_THREADS=8
|
|
THREAD_BATCH=8
|
|
|
|
# f16 K/V: an agentic checkpoint is the wrong place to spend KV precision.
|
|
CACHE_TYPE_K=f16
|
|
CACHE_TYPE_V=f16
|
|
CTX_CHECKPOINTS=8
|
|
CACHE_RAM=8192
|
|
|
|
# Sampling defaults for requests that send none -- the values the vLLM
|
|
# predecessor served on this endpoint (`--override-generation-config`), so a
|
|
# client sees no change across the runtime swap. The model card's own
|
|
# recommendation is temp 1.0 / top_p 0.95; the harness sets its own per model in
|
|
# models.yml, so this is the floor, not the contract.
|
|
TEMPERATURE=0.7
|
|
TOP_P=0.95
|
|
TOP_K=20
|
|
MIN_P=0.0
|
|
PRESENCE_PENALTY=0.0
|
|
|
|
# Reasoning on, projected into reasoning_content (deepseek format) with no
|
|
# budget: the model decides how long to think.
|
|
REASONING=on
|
|
REASONING_FORMAT=deepseek
|
|
REASONING_BUDGET=-1
|
|
|
|
# Chat template: empty = the one embedded in the GGUF (Qwen3.8's own).
|
|
CHAT_TEMPLATE_FILE=
|
|
CHAT_TEMPLATE_KWARGS='{"enable_thinking":true,"preserve_thinking":true}'
|
|
|
|
# Speculative decoding: the DFlash2 block-diffusion drafter PLUS the draftless
|
|
# n-gram matcher. Measured against the drafter alone on 2026-09-16 (tables
|
|
# below): the chain is byte-identical to DFlash2 by itself where n-grams cannot
|
|
# match, and ~2.6x it where they can. DFlash2's GGUF carries block_size 8, so at
|
|
# most 7 draft tokens per verification step (llama.cpp asserts
|
|
# n_max <= block_size - 1); 7 is also what the drafter was published with. The
|
|
# drafter rides ROCm1, the card that ends up holding the target's last layers.
|
|
SPEC_TYPE=draft-dflash,ngram-mod
|
|
SPEC_DRAFT_N_MAX=7
|
|
SPEC_DRAFT_NGL=999
|
|
SPEC_DRAFT_DEVICE=ROCm1
|
|
SPEC_DRAFT_TYPE_K=f16
|
|
SPEC_DRAFT_TYPE_V=f16
|
|
|
|
# MTP (the model's own head) vs the drafter -- MEASURED 2026-09-16 (temperature
|
|
# 0, 1k prompt / 512 out; the autoregressive baseline and both MTP depths were
|
|
# run against the deployed configuration in one session, same binary, same
|
|
# prompts):
|
|
#
|
|
# none 17.7 tok/s card1 26.07 GB
|
|
# draft-mtp n=3 32.4 tok/s 58 % accepted card1 29.35 GB
|
|
# draft-mtp n=7 26.7 tok/s 33 % accepted card1 29.65 GB
|
|
# draft-dflash 7 43.5 tok/s 41 % accepted card1 29.42 GB
|
|
#
|
|
# All four produced IDENTICAL greedy text, so verification is lossless whichever
|
|
# proposer runs. DFlash2 is worth 2.46x over autoregressive and 34 % over the
|
|
# best MTP; deeper MTP drafting costs more than it returns (n=7 accepts 33 % of
|
|
# 147 proposals, n=3 accepts 58 % of 72). The MTP head is not free either:
|
|
# selecting it loads blk.64.nextn.* and adds ~3.3 GB to the card that holds it,
|
|
# against 2.06 GB for the drafter's file. Do not switch this without
|
|
# re-measuring.
|
|
#
|
|
# THE TWO CANNOT BE CHAINED. `--spec-type draft-mtp,draft-dflash` dies at load:
|
|
# context type MTP requested but model doesn't contain MTP layers
|
|
# failed to create MTP context
|
|
# A chain has ONE draft context, and MTP builds against whatever model that
|
|
# context holds -- here the DFlash2 file, which has no MTP layers. MTP's head is
|
|
# only loaded when MTP IS the draft model ("creating MTP draft context against
|
|
# the target model ..."), so a chain of the two is a structural dead end, not a
|
|
# tuning question. See serverAppConfigs-docs/LLM/frank-medium-llamacpp-dflash2.md.
|
|
|
|
# ngram-mod: the draftless n-gram matcher (CPU hash table in host RAM, no VRAM,
|
|
# no model file, no draft context). It joins the chain unconditionally --
|
|
# unlike MTP, which needs a draft context and therefore cannot share one with
|
|
# DFlash2. Verified on the loaded server: with ngram-mod as the ONLY spec type,
|
|
# a prose prompt produces ZERO drafts (plain autoregressive) while a
|
|
# prompt-echo prompt accepts 100 % of them, so its drafts are unmistakable.
|
|
#
|
|
# WINDOW MEASURED 2026-09-16 (chain at each window, decode tok/s):
|
|
#
|
|
# n_min/n_max prose 1k/512 prompt-echo 1.5k/400
|
|
# 48/64 43.9 200.6 <- deployed
|
|
# 16/32 36.0 161.0
|
|
# 8/16 36.2 113.8
|
|
#
|
|
# The long window is the right one, and not only because it wins on echo: a
|
|
# SHORT window makes the matcher propose on short fragments of ordinary prose,
|
|
# where the proposals are rejected and the verification still costs -- which is
|
|
# the "ngram hurts" result the fleet measured on other payloads twice before.
|
|
# With 48/64 the chain is byte-identical to DFlash2 alone on prose (same 119
|
|
# drafts / 49 accepted) and on the identity prompt (70/53).
|
|
#
|
|
# Do not shorten these without re-running scripts/bench-spec-ab.py: the
|
|
# no-penalty property is what makes the chain safe as a default.
|
|
SPEC_NGRAM_N_MATCH=24
|
|
SPEC_NGRAM_N_MIN=48
|
|
SPEC_NGRAM_N_MAX=64
|
|
|
|
# Text only: the server must not autoload a vision tower. Vision stays on
|
|
# frank-small (Dankclaw, RTX 3090), which is the fleet's image endpoint.
|
|
NO_MMPROJ=1
|