Frank
6169278911
Concurrency cap trimmed to the real fleet size. Each slot is 111.0 MiB of O(1) state, so this hands ~111 MiB back on a host sitting at 7.1 GiB left for everything else. Note the slots already oversubscribed the pool (4 x 262144 > 524288), so admission was pool-bound regardless: at most two full-length conversations, or four at 131k. This does not change how much context fits -- it caps simultaneous requests at three, and a fourth now queues.
198 lines
11 KiB
INI
198 lines
11 KiB
INI
# Quadlet unit: frank-large (rootless, boot-persistent).
|
|
#
|
|
# Install path on dankclaw: ~/.config/containers/systemd/frank-large.container
|
|
# Unit name: frank-large.service (container name: frank-large)
|
|
#
|
|
# The large inference service, since 2026-09-11 the halogen-flash-server
|
|
# runtime serving peonist-ai/halogen-qwen3.8-flash-next (Qwen3.8-Flash-Next,
|
|
# w4b .hgn checkpoint + quality overlay sidecar). It replaced the llama.cpp /
|
|
# kingjones30-ROCmFPX STRIX deployment because the engine is ~4x faster on
|
|
# prefill (the dominant cost of any real prompt) on this exact SKU.
|
|
#
|
|
# SHAPE. The image runs both halves in one container: the engine on container
|
|
# loopback (:8730, UNAUTHENTICATED — never publish it) and the OpenAI
|
|
# front-end on :8731, published here as host 7770 so the fleet's clients,
|
|
# services.json probe and docs keep the port they have always used. Same for
|
|
# HALOGEN_MODEL_ID=frank-large: it is the id at /v1/models, in /health and in
|
|
# every response, so no client had to be renamed. Halogen never rejects a
|
|
# request for naming a different model, it just serves it.
|
|
#
|
|
# DEVICES. gfx1151 through the amdgpu/KFD stack: /dev/kfd plus the DRM render
|
|
# node. Both are 0666 on this host, so the rootless user namespace can open
|
|
# them (id dank is also in render/video). seccomp=unconfined and --ipc=host are
|
|
# the image's documented requirements; memlock must be unlimited.
|
|
#
|
|
# DO NOT name an environment variable TEMP, HOST or GPU_MAX_HEAP_SIZE: the HIP
|
|
# runtime reads bare TEMP for its JIT cache path (2026-08-13 incident).
|
|
#
|
|
# MEMORY. Weights are pinned (HALOGEN_FLASH_PIN_TRUNK default 1) — that is the
|
|
# configuration the published decode numbers were measured with, and `free`,
|
|
# MemAvailable and every monitor built on them will overstate free memory by
|
|
# the size of the model (~68 GiB) because the kernel counts the locked weights
|
|
# as reclaimable page cache. Halogen prints the corrected figure at startup.
|
|
# The pinned trunk means this container holds most of the host; a co-tenant
|
|
# that then takes the remainder can stall both for minutes at full CPU with no
|
|
# disk activity and no output. That is documented behaviour, not a crash, and
|
|
# the escape hatch is HALOGEN_FLASH_PIN_TRUNK=0 (at several times the decode
|
|
# cost). Sizing is chosen for a SHARED 121 GiB host, and HALOGEN_KV_POOL_FIT
|
|
# stays on as the safety net: if the machine refuses the configured pool the
|
|
# engine lowers it itself and prints what it settled on. Read that ledger on
|
|
# every restart — it is the ground truth for sizing, not this comment.
|
|
#
|
|
# DOUBLED 2026-09-12: pool 524,288 positions (~14.4 GiB of KV at the
|
|
# measured 28 KiB/position). This did NOT fit on the first attempt. The
|
|
# engine's own ledger for the prior 262,144 config was 68.0 weights + 7.2
|
|
# pool + 21.1 working = 96.3 GiB held, 12.1 GiB left on the host, and its
|
|
# pre-flight arithmetic is: 121 GiB - 67.7 resident weights - 24.0 reserve
|
|
# = 29.5 GiB of device budget, which has to cover the pool AND the prefill
|
|
# arena together. 524,288 with the 32,768-token arena needs 35.0 GiB, so
|
|
# HALOGEN_KV_POOL_FIT lowered the pool straight back to 262,144 and the
|
|
# deploy still reported healthy. The doubling only becomes real together
|
|
# with HALOGEN_MAX_TOK=16384 further down, which halves the arena and brings
|
|
# the need to ~24.9 GiB. Read the `kv pool:` lines after every restart —
|
|
# a green health check does NOT mean the pool you asked for is the pool you got.
|
|
#
|
|
# WEIGHTS. HALOGEN_DOWNLOAD fetches the whole weights repo on FIRST START ONLY
|
|
# (the entrypoint checks whether the checkpoint is absent) into the bind mount
|
|
# below, which must therefore be read-WRITE. huggingface_hub resumes partial
|
|
# files natively, and the quadlet runs the container with --replace --rm, so a
|
|
# restart mid-fetch continues rather than starting over. Roughly 127 GB: the
|
|
# 115.55 GiB checkpoint, the 2.31 GiB quality overlay, the 0.84 GiB vision
|
|
# tower and the tokenizer. The repo is public and ungated, so no token is
|
|
# needed; later starts open no outbound connections at all.
|
|
#
|
|
# VISION. HALOGEN_VISION_TOWER=1 finds the sidecar beside the checkpoint. This
|
|
# is the fleet's only image input since the FLM NPU endpoint was retired on
|
|
# 2026-09-11; audio input has no replacement.
|
|
#
|
|
# CLIENT CONTRACT (see serverAppConfigs-docs/LLM/halogen-flash-server.md).
|
|
# There are no server-side sampler defaults: a request that sends no
|
|
# temperature decodes GREEDY. The per-request budget defaults to 8,192 tokens
|
|
# and REASONING COUNTS AGAINST IT, so a budget that runs out mid-thought
|
|
# returns finish_reason "length" with empty content and the partial reasoning
|
|
# in reasoning_content. The cap is 65,536; above it a request is a 400, never a
|
|
# silent truncation.
|
|
#
|
|
# IMAGE. The unit runs the localhost/-aliased tag: this host's podman quadlet
|
|
# path cannot resolve registry-prefixed refs from local storage at create
|
|
# time. deploy-remote.sh pulls the ghcr.io ref and re-tags it before the
|
|
# restart. Pull=never keeps boots off the registry.
|
|
[Unit]
|
|
Description=frank-large — halogen-flash-server, Qwen3.8-Flash-Next (w4b) on gfx1151
|
|
After=network-online.target
|
|
|
|
[Container]
|
|
ContainerName=frank-large
|
|
Image=localhost/peonist-ai/halogen-flash-server:0.5.8
|
|
# Published port stays 7770: Hermes, open-webui, the harness and the homepage
|
|
# probe all point here. 8730 (the engine) is deliberately not published.
|
|
PublishPort=7770:8731
|
|
AddDevice=/dev/kfd
|
|
AddDevice=/dev/dri
|
|
# Read-write: the first start downloads into it. Contains only weights.
|
|
Volume=/home/dank/models/halogen:/models
|
|
# Fetch the weights on first start only (absent checkpoint gates it).
|
|
Environment=HALOGEN_DOWNLOAD=peonist-ai/halogen-qwen3.8-flash-next
|
|
# Fleet identity: the id at /v1/models, /health and every response body.
|
|
Environment=HALOGEN_MODEL_ID=frank-large
|
|
# Native context of the model. Matches what both clients declare.
|
|
Environment=HALOGEN_CTX=262144
|
|
# Doubled 2026-09-12 from the 262144 this had run since 09-11: two full-length
|
|
# conversations resident at once, or four at 131k, instead of one.
|
|
Environment=HALOGEN_KV_POOL_POSITIONS=524288
|
|
# Concurrency cap. Each slot is 111.0 MiB of O(1) state; the KV is ONE
|
|
# 524288-position pool carved into per-request regions, so slots cap how many
|
|
# requests run at once while the pool binds how many positions exist. These
|
|
# slots OVERSUBSCRIBE the pool (4 x 262144 > 524288), so admission was always
|
|
# pool-bound -- at most two full-length conversations, or four at 131k.
|
|
# LOWERED 4 -> 3 on 2026-09-12: frees ~111 MiB on a host with 7.1 GiB left,
|
|
# and three users is the real fleet size. A fourth concurrent request now
|
|
# queues behind the three rather than contending.
|
|
Environment=HALOGEN_KV_SLOTS=3
|
|
# Making the doubling stick is budget arithmetic, all of it. ONE budget covers
|
|
# the KV pool, the prefill arena and the vision tower together:
|
|
#
|
|
# budget = 121.2 host - 67.7 resident weights - reserve
|
|
# need = KV (~28 KiB/position) + arena + vision (1.97 measured)
|
|
# arena = 3.80 GiB + 8.40 GiB x (HALOGEN_MAX_TOK / 16384)
|
|
#
|
|
# The arena term is linear in max_tok, and it reproduces five live restarts
|
|
# AND upstream's three published "on the device" figures to within 0.1 GiB —
|
|
# note those published figures are pool+arena totals, not pool alone, which is
|
|
# the misreading that first made a doubling look affordable here. Every corner
|
|
# this box offered at a reserve of 24:
|
|
#
|
|
# 16384 -> need 28.6 vs 29.5 FITS, 0.9 spare (doubling, 8-9% prefill cost)
|
|
# 32768 -> need 37.0 vs 29.5 POOL CLAMPED to 262144, deploy still green
|
|
# 65536 -> need 46.5 vs 29.5 OOM, will not boot; unit still reads ACTIVE
|
|
#
|
|
# None of those three gave both features. Dropping the reserve to 15 moves the
|
|
# budget to 38.5, so 32768's need of 37.0 fits with 1.5 spare: full prefill
|
|
# AND the doubled pool, paid for out of the n-gram page cache instead of out of
|
|
# either feature. THE TWO SETTINGS ARE A MATCHED PAIR, NOT independent tunables
|
|
# — raise the reserve back to 24 and the pool silently clamps to 262144 again.
|
|
Environment=HALOGEN_MAX_TOK=32768
|
|
# RAM left for the n-gram table the engine reads through the page cache.
|
|
# LOWERED 2026-09-12 from 24 (vendor default is 20) to buy the doubled pool at
|
|
# full prefill speed. The fit check's OWN requirement is the line to honour —
|
|
# read from a clamped boot, not modelled:
|
|
# "524288 positions need ~35.0 GiB (plus 1.5 of margin)" -> budget >= 36.5
|
|
# budget = 121.2 host - 67.7 weights - reserve
|
|
# reserve 16 -> 37.5 (1.0 spare); 15 -> 38.5 (2.0 spare, deployed); 18 -> 35.5
|
|
# CLAMPS the pool to 262144. Do not raise past 16.
|
|
#
|
|
# CEILING IS 16, AND 16 BUYS NOTHING. Tested live: 15 -> 16 changed the fit
|
|
# margin only. The server held 103.5 GiB and reported "7.1 GiB left for
|
|
# everything else" at BOTH settings, because this reserve feeds the fit-check
|
|
# budget and is not an allocation — actual footprint is weights + KV + arena +
|
|
# vision, none of which it touches. A higher reserve therefore cannot give the
|
|
# host memory back; it can only take the pool away. 15 keeps the larger margin.
|
|
#
|
|
# Measured at 15 before that test: pool reserved at 524288 with no clamp and no
|
|
# WARNING, and the server held 103.5 GiB. The ledger
|
|
# reads "host memory left for everything else: 310 contiguous 2 MiB blocks
|
|
# (7.1 GiB total)" — against 2081 blocks / 12.1 GiB at the 24-reserve
|
|
# baseline. All 28 co-tenant containers stayed up (~4.3 GiB working set).
|
|
#
|
|
# The price is that the engine volunteers this note on every boot now:
|
|
# when it runs out, BOTH they and this server can stall for minutes at a
|
|
# time at full CPU with no disk activity and no output, which is not a
|
|
# crash and needs no restart.
|
|
# That is the failure mode to watch, and it is NOT the legible one predicted
|
|
# above: a minutes-long stall that looks like a hang is harder to diagnose
|
|
# than a slow prompt. If it happens, the reserve has no headroom left to give
|
|
# — the remedy is HALOGEN_KV_POOL_POSITIONS=262144 (hands back 7.2 GiB), or
|
|
# HALOGEN_MAX_TOK=16384 (hands back 8.4) with reserve then free to rise to 24.
|
|
Environment=HALOGEN_HOST_RESERVE_GIB=15
|
|
# Image input (the sidecar ships inside the weights repo).
|
|
Environment=HALOGEN_VISION_TOWER=1
|
|
# Verbose engine logging: the vendor's first-line evidence for load,
|
|
# allocation and admission questions. Shipping it on means an incident report
|
|
# already has the full startup account instead of needing a restart-into-debug.
|
|
# HALOGEN_DMALLOC_LOG is deliberately NOT set — it logs every allocation
|
|
# over 64 MB, which is steady-state noise here; raise it only for a live
|
|
# OOM hunt.
|
|
Environment=HALOGEN_VERBOSE=1
|
|
# Required by the image: the engine maps the checkpoint and registers it with
|
|
# the GPU in place, which needs host IPC and an unconfined seccomp profile.
|
|
PodmanArgs=--ipc=host --security-opt seccomp=unconfined
|
|
Ulimit=memlock=-1:-1
|
|
# The image ships its own HEALTHCHECK; this pins it. /health asks the ENGINE
|
|
# for a PONG before answering, so 200 means "ready to serve", not "process
|
|
# alive". During the first-start download it stays unhealthy by design.
|
|
HealthCmd=halogen-healthcheck api
|
|
HealthInterval=30s
|
|
HealthTimeout=10s
|
|
HealthRetries=3
|
|
HealthStartPeriod=300s
|
|
Pull=never
|
|
|
|
[Service]
|
|
# The first start reads ~68 GiB off disk and pins it before serving.
|
|
TimeoutStartSec=900
|
|
Restart=on-failure
|
|
RestartSec=10
|
|
|
|
[Install]
|
|
WantedBy=default.target
|