Frank
b312042706
The operator's revised spec: batch x3 (6144/1536), parallel 2, a 1.5 GiB per-card floor, and the context maximised inside it. Measured at 262144 with the old 38:27 split, 3x batch was brutally asymmetric: ROCm1 (output layers + the drafter's graphs) paid ~3.3 GiB where ROCm0 paid ~1.7, leaving the draft-carrying card at 0.08 GiB free against ROCm0's 3.78. One -ts step is worth ~1.5 GiB at this batch, so the balance is a measurement: 41:24 overshot (1.47 / 2.38), 40:25 landed at 1.92 / 1.96 GiB free. That balance is also what maximises the context -- an unbalanced split would have to buy its headroom out of CTX_SIZE, and CTX_SIZE is already at the model's trained window (262144), now split over two slots of 131072. Verified under two concurrent 1832-token prompts: 200/200, 1.87 / 1.86 GiB free, n_slots = 2, n_ctx_slot = 131072, tool calls intact, and DSpark drafting on BOTH slots (acceptance 0.38/0.22 and 0.52/0.43). 8192/2048 does not fit at this context at all: its 2020 MiB pp buffer fails to allocate on ROCm1, and 4096/1024 fits but leaves 1.11 GiB -- both recorded in the env's sizing table. The unit seam now models both cards (share + draft + ubatch-scaled buffers, calibrated to the rocm-smi figures to within 0.002%), asserts the 1.5 GiB floor on each, and asserts the two cards stay within 0.5 GiB of each other. Both assertions were confirmed to FAIL on a deliberately bad config (ubatch 8192, and a 1:1 split) rather than pass by construction.
253 lines
13 KiB
Bash
253 lines
13 KiB
Bash
# Tunables for frank-medium (ajgazin/Swift-Qwen3.8-27B-Uncensored-Dynamic-MTP
|
|
# UD-Q8_K_XL + magnitudedev/Qwen3.8-27B-DSpark-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: magnitudedev/Qwen3.8-27B-DSpark-GGUF @ Q8_0, 1.27 GiB: 5 layers,
|
|
# hidden 5120, block-diffusion proposal with the Markov head (dspark).
|
|
# Decoding stays lossless -- the target verifies every drafted token. Its KV
|
|
# spans the whole context (see SIZING): unlike DFlash2 it declares no sliding
|
|
# window, and that is what the tensor split below pays for.
|
|
#
|
|
# 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 AND its KV ride the second. The loader's compute buffers are part
|
|
# of what is seen below -- they are allocated at load, not per request, and they
|
|
# scale with --ubatch-size:
|
|
#
|
|
# CTX split batch slots GPU 0 free GPU 1 free note
|
|
# 262144 1,1 2048 1 8.64 GiB 4.43 GiB DFlash2, day's start
|
|
# 262144 38,27 2048 1 5.49 GiB 3.41 GiB DSpark, 1 slot
|
|
# 262144 38,27 6144 2 3.78 GiB 0.08 GiB 3x batch is ASYMMETRIC
|
|
# 262144 40,25 6144 2 1.87 GiB 1.86 GiB <- 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.
|
|
#
|
|
# WHY THE SPLIT IS 40:25, AND WHY IT DEPENDS ON THE BATCH. Two effects pull in
|
|
# opposite directions:
|
|
# * THE DRAFT KEEPS ITS OWN FULL-CONTEXT KV ON ROCm1. The draft context is
|
|
# built with `n_ctx = llama_n_ctx(ctx_tgt)` (common/speculative.cpp), so
|
|
# DSpark -- which, unlike DFlash2 (`sliding_window` 2048, ~40 MiB), declares
|
|
# no window -- caches 5 layers x 2 x 8 kv heads x 128 dim x 2 B = 20 KiB per
|
|
# position: 5.0 GiB at 262144. At a 1:1 split that put ROCm1 at 33.9 GB of
|
|
# 34.2 GB and the draft's first graph capture died with `ROCm error: out of
|
|
# memory` (common_speculative_impl_draft_dflash::process). Hence 38:27.
|
|
# * THE BIGGER BATCH COSTS ROCm1 ABOUT TWICE WHAT IT COSTS ROCm0 (~3.3 vs
|
|
# ~1.7 GiB going 2048/512 -> 6144/1536 at 262144): ROCm1 holds the output
|
|
# layers AND the drafter's graphs. At 38:27 that left ROCm1 at 0.08 GiB
|
|
# free against ROCm0's 3.78 -- the reason for the rebalance.
|
|
# One -ts step shifts ~1.5 GiB of load between the cards at this batch, so the
|
|
# balance is found by measurement, not arithmetic. 40:25 is the measured
|
|
# balance (a 0.05 GiB gap) and it is also what MAXIMISES the context: with the
|
|
# floor at ~1.5 GiB per card, an unbalanced split would have to buy its
|
|
# headroom out of CTX_SIZE.
|
|
#
|
|
# A FAULT TO WATCH. A 39:26 split, at 1x batch / 1 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,
|
|
# i.e. a fault in the cross-card boundary copy, this layer split's hot path. It
|
|
# has not reproduced (38:27 served the whole e2e gate and a burst of requests;
|
|
# 40:25 has served this file's verification battery), but the signature is
|
|
# worth recognising -- it is NOT an OOM, and no amount of headroom prevents it.
|
|
#
|
|
# 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-DSpark-GGUF
|
|
DRAFT_MODEL_FILE=Qwen3.8-27B-DSpark-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
|
|
|
|
# 40:25 -- the measured balance at the deployed batch, and the point that
|
|
# maximises CTX_SIZE: ROCm1 carries the drafter, its full-context KV and the
|
|
# output layers, so it takes fewer target layers. See SIZING above; one -ts
|
|
# step is worth ~1.5 GiB at this batch, so do not move it without re-measuring.
|
|
TENSOR_SPLIT=40,25
|
|
|
|
NGL=999
|
|
# Auto-fit has no business resizing a context we set explicitly.
|
|
FIT=off
|
|
FLASH_ATTN=on
|
|
|
|
# The model's full window (n_ctx_train 262144) divided over TWO slots, so each
|
|
# conversation gets 131072 -- verified at load as `n_slots = 2, n_ctx_slot =
|
|
# 131072`. --parallel DIVIDES --ctx-size, so more slots would shrink every
|
|
# conversation rather than grow the cache.
|
|
CTX_SIZE=262144
|
|
PARALLEL=2
|
|
|
|
# 3x the build's defaults (2048/512). --ubatch-size is the physical batch the
|
|
# graph is built at and therefore what the compute buffers cost: at 262144 this
|
|
# setting needs ~1.7 GiB more on ROCm0 and ~3.3 GiB on ROCm1 than 2048/512 does
|
|
# -- which is what forced the rebalance above. 8192/2048 does not fit at all
|
|
# here: its 2020 MiB pp buffer fails to allocate on ROCm1.
|
|
BATCH_SIZE=6144
|
|
UBATCH_SIZE=1536
|
|
|
|
# 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
|
|
# Context checkpoints: 0 is the build's default -- no per-slot KV snapshots, so
|
|
# a re-sent or rewound conversation re-prefills instead of rewinding. Stated
|
|
# explicitly so the tunable stays visible rather than merely absent.
|
|
CTX_CHECKPOINTS=0
|
|
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 DSpark block-diffusion drafter PLUS the draftless
|
|
# n-gram matcher. DSpark's GGUF carries block_size 7, so at most 6 draft
|
|
# tokens per verification step (llama.cpp asserts n_max <= block_size - 1).
|
|
# The drafter rides ROCm1, the card that ends up holding the target's last
|
|
# layers.
|
|
SPEC_TYPE=draft-dspark,ngram-mod
|
|
SPEC_DRAFT_N_MAX=6
|
|
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
|