Frank
cb25796a6b
The image/.rad/template gates are require_image/require_min_mib/require_file, and the gates an operator can only reach on the host (GPU nodes, the ttm pages cap, the run line) are now drivable: FRANK_ARCHON_DEV_KFD, FRANK_ARCHON_DEV_DRI, FRANK_ARCHON_TTM_SYSFS and FRANK_ARCHON_LOG default to the production paths. Seven new seam tests EXECUTE the serve script against fixtures (stub podman, stub nodes, stub sysfs, temp payload) and assert exit status, the refusal words and the engine argv. The old text-grep gate test is deleted: it pinned the words of the source, not the behaviour.
205 lines
11 KiB
Bash
Executable File
205 lines
11 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# serve-frank-archon.sh — frank-archon endpoint: radiance (StillDeadcode,
|
|
# Apache-2.0) serving the OFFICIAL Qwen/Qwen3.8-Flash-Next-FP8 checkpoint at
|
|
# NATIVE block-FP8 precision from a rad-convert container
|
|
# (/home/dank/models/rad/qwen4exp-fp8-native.rad), on BOTH R9700s (TP=2,
|
|
# wht6 wire), dankserver :7770. 2026-10-05 cutover from FreeToken (PR #587,
|
|
# one card; git tag frank-archon-freetoken-pr587-20261005 is the
|
|
# pre-cutover state).
|
|
#
|
|
# The run line below IS the engine argv: the image's entrypoint is the
|
|
# engine and its tools sit beside it on PATH. Unlike every predecessor
|
|
# there is no per-boot VRAM planner to second-guess: the boot ledger in the
|
|
# log states every budget before anything is allocated (weights vs KV
|
|
# split, the expert host pool's coverage of the worst case, the PLE pin,
|
|
# the P2P answer per pair) — read it after every resize.
|
|
# Deployed shape (2026-10-11): 2 decode slots x 200,000 tokens, bf16
|
|
# (unquantized) KV in a 6,912 MiB pool, the weights slab cut to 22,208 MiB to
|
|
# pay for it, 44 GiB/rank pinned expert pool, MTP depth 2, prefix cache host
|
|
# 8 GiB + disk 64 GiB, PLE pinned in RAM.
|
|
#
|
|
# The root unit (scripts/frank-archon.service, User=dank,
|
|
# LimitMEMLOCK=infinity) grants the pin budget: 2 x 44 GiB expert pools +
|
|
# the 47.7 GiB PLE table + 8 GiB prefix host tier — ~147 GiB of pinned
|
|
# pages, which is ALSO why this script refuses to start when ttm's
|
|
# pages_limit/pages_max cap is under FRANK_ARCHON_TTM_MIN_MIB (see below).
|
|
set -euo pipefail
|
|
|
|
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
|
|
|
# The artifact gates are the shared library: the serve script and the
|
|
# deployer must refuse the same missing/truncated payload with the same
|
|
# words (the fleet law from the 2026-10-01 crash-loop).
|
|
export GATE_PREFIX=frank-archon
|
|
# shellcheck disable=SC1091
|
|
source "$SCRIPT_DIR/lib/llm-gates.sh"
|
|
ENV_FILE="${FRANK_ARCHON_ENV_FILE:-$SCRIPT_DIR/frank-archon.env}"
|
|
|
|
if [ ! -f "$ENV_FILE" ]; then
|
|
echo "ERROR: frank-archon env file absent: $ENV_FILE" >&2
|
|
exit 1
|
|
fi
|
|
set -a
|
|
# shellcheck disable=SC1090
|
|
source "$ENV_FILE"
|
|
set +a
|
|
|
|
: "${FRANK_ARCHON_IMAGE:?FRANK_ARCHON_IMAGE must name the radiance image}"
|
|
: "${FRANK_ARCHON_MODEL_DIR:?FRANK_ARCHON_MODEL_DIR must name the .rad dir}"
|
|
: "${FRANK_ARCHON_MODEL_FILE:?FRANK_ARCHON_MODEL_FILE must name the .rad file}"
|
|
: "${FRANK_ARCHON_STATE_DIR:?FRANK_ARCHON_STATE_DIR must name the /data state dir}"
|
|
: "${FRANK_ARCHON_CONTAINER:?FRANK_ARCHON_CONTAINER must name the container}"
|
|
: "${FRANK_ARCHON_SERVED_NAME:?FRANK_ARCHON_SERVED_NAME must name the alias}"
|
|
: "${FRANK_ARCHON_PORT:?FRANK_ARCHON_PORT must be the port}"
|
|
: "${FRANK_ARCHON_TEMPLATE:?FRANK_ARCHON_TEMPLATE must name the chat template}"
|
|
: "${FRANK_ARCHON_TP:?FRANK_ARCHON_TP must be set}"
|
|
: "${FRANK_ARCHON_TP_WIRE:?FRANK_ARCHON_TP_WIRE must be set}"
|
|
: "${FRANK_ARCHON_MAX_SEQS:?FRANK_ARCHON_MAX_SEQS must be set}"
|
|
: "${FRANK_ARCHON_MAX_MODEL_LEN:?FRANK_ARCHON_MAX_MODEL_LEN must be set}"
|
|
: "${FRANK_ARCHON_PLACEMENT:?FRANK_ARCHON_PLACEMENT must be set}"
|
|
: "${FRANK_ARCHON_HOST_POOL_MIB:?FRANK_ARCHON_HOST_POOL_MIB must be set}"
|
|
: "${FRANK_ARCHON_GPU_HEADROOM_MIB:?FRANK_ARCHON_GPU_HEADROOM_MIB must be set}"
|
|
: "${FRANK_ARCHON_VRAM_WEIGHTS_MIB:?FRANK_ARCHON_VRAM_WEIGHTS_MIB must be set}"
|
|
: "${FRANK_ARCHON_VRAM_KV_MIB:?FRANK_ARCHON_VRAM_KV_MIB must be set}"
|
|
: "${FRANK_ARCHON_KV_DTYPE:?FRANK_ARCHON_KV_DTYPE must be set}"
|
|
: "${FRANK_ARCHON_SPEC_TOKENS:?FRANK_ARCHON_SPEC_TOKENS must be set}"
|
|
: "${FRANK_ARCHON_MAX_BATCHED_TOKENS:?FRANK_ARCHON_MAX_BATCHED_TOKENS must be set}"
|
|
: "${FRANK_ARCHON_PREFIX_HOST_MIB:?FRANK_ARCHON_PREFIX_HOST_MIB must be set}"
|
|
: "${FRANK_ARCHON_PREFIX_DISK_MIB:?FRANK_ARCHON_PREFIX_DISK_MIB must be set}"
|
|
: "${FRANK_ARCHON_NGRAM_PLACEMENT:?FRANK_ARCHON_NGRAM_PLACEMENT must be set}"
|
|
: "${FRANK_ARCHON_TTM_MIN_MIB:?FRANK_ARCHON_TTM_MIN_MIB must be set}"
|
|
: "${FRANK_ARCHON_RAD_MIN_MIB:?FRANK_ARCHON_RAD_MIN_MIB must be set}"
|
|
|
|
# The image gate is the digest-pinned ref itself: a name@sha256 ref exists
|
|
# in storage only if THAT manifest was pulled — a retagged look-alike or a
|
|
# newer latest does not satisfy it. One command, no pipefail/grep race (the
|
|
# 2026-09-30 lesson). Runs as dank: the unit's process uses dank's ROOTLESS
|
|
# podman storage (root unit, User=dank — the fleet's frank-archon shape).
|
|
require_image "$FRANK_ARCHON_IMAGE" \
|
|
"podman pull docker://stilldeadcode/radiance:latest (as dank)" || exit 1
|
|
|
|
# The payload gate: the .rad container file, sized. A truncated convert
|
|
# would otherwise buy a guaranteed long-timeout boot instead of this fast
|
|
# failure. The staging dir / raw checkpoint are NOT this script's concern
|
|
# (the convert script built the file; its rad-info output is the record).
|
|
require_min_mib "$FRANK_ARCHON_MODEL_DIR/$FRANK_ARCHON_MODEL_FILE" \
|
|
container "$FRANK_ARCHON_RAD_MIN_MIB" \
|
|
"build it: scripts/convert-swift15-w4dn8.sh (rad-info is the record)" || exit 1
|
|
|
|
require_file "$FRANK_ARCHON_TEMPLATE" template \
|
|
"the chat template is vendored: scripts/qwen38-froggeric-v22.5.jinja" || exit 1
|
|
|
|
mkdir -p "$FRANK_ARCHON_STATE_DIR/kvcache/frank-archon"
|
|
# The engine's create is NOT recursive: with only the state dir mounted, its
|
|
# "cannot create /data/kvcache/frank-archon: No such file or directory"
|
|
# left the SSD prefix tier off (measured 2026-10-06 boot ledger). Pre-create
|
|
# the full path on the host so the tier opens on first boot.
|
|
|
|
mkdir -p "$FRANK_ARCHON_STATE_DIR/tune"
|
|
# rad-tune's kernel-selection cache (see the runbook's "Tuning levers"):
|
|
# the engine's selector reads $RADIANCE_HOME/tune/<machine>.tune at boot;
|
|
# $RADIANCE_HOME defaults to /opt/radiance, which lives in the image, so
|
|
# the cache must ride a host mount or it dies with the --rm container
|
|
# that wrote it. The dir is pre-created for the same reason as kvcache
|
|
# (the engine's create is not recursive).
|
|
|
|
# GPU access is mandatory; the node paths are knobs so the seam can drive
|
|
# this gate on a box without AMD GPUs (production defaults).
|
|
DEV_KFD="${FRANK_ARCHON_DEV_KFD:-/dev/kfd}"
|
|
DEV_DRI="${FRANK_ARCHON_DEV_DRI:-/dev/dri}"
|
|
if [ ! -e "$DEV_KFD" ] || [ ! -d "$DEV_DRI" ]; then
|
|
echo "ERROR: GPU device nodes absent ($DEV_KFD, $DEV_DRI)" >&2
|
|
exit 1
|
|
fi
|
|
|
|
# TTM preflight: the pinned ledger (~2 x 40 GiB pools + 47.7 GiB PLE + 4 GiB
|
|
# prefix host = ~132 GiB) rides TTM's shared pages, capped by ttm's
|
|
# pages_limit (the current kernel exposes NO pages_max; the cap function
|
|
# takes the min over the knobs that exist). Below FRANK_ARCHON_TTM_MIN_MIB
|
|
# the load dies mid-pin with an allocator error instead of this named
|
|
# refusal — raise the knob first (runtime sysfs write; kernel cmdline
|
|
# fallback + one reboot only if the file is read-only), see the runbook.
|
|
# RAISED 2026-10-05 pre-cutover to 52,428,800 pages = 200 GiB.
|
|
ttm_cap_mib() {
|
|
# min over the knobs THIS kernel exposes — the current kernel has
|
|
# pages_limit only (no pages_max); a knob that is absent is skipped,
|
|
# not a zero (a zero would refuse a healthy cap).
|
|
local v cur="" dir
|
|
dir="${FRANK_ARCHON_TTM_SYSFS:-/sys/module/ttm/parameters}"
|
|
for p in "$dir/pages_limit" "$dir/pages_max"; do
|
|
[ -r "$p" ] || continue
|
|
v="$(cat "$p" 2>/dev/null)" || continue
|
|
[ -n "$v" ] || continue
|
|
v=$(( v * 4 / 1024 ))
|
|
if [ "$v" -lt "${cur:-999999999}" ]; then cur=$v; fi
|
|
done
|
|
echo "${cur:-0}"
|
|
}
|
|
TTM_CAP="$(ttm_cap_mib)"
|
|
if [ "$TTM_CAP" -lt "$FRANK_ARCHON_TTM_MIN_MIB" ]; then
|
|
echo "ERROR: ttm pages cap is ${TTM_CAP} MiB, the pinned ledger needs >= $FRANK_ARCHON_TTM_MIN_MIB" >&2
|
|
echo "frank-archon: raise /sys/module/ttm/parameters/pages_limit (and pages_max if the kernel exposes one) to >= $FRANK_ARCHON_TTM_MIN_MIB in 4 KiB pages" >&2
|
|
exit 1
|
|
fi
|
|
|
|
# A crashed/killed unit can leave the container name registered (systemd
|
|
# SIGKILLs conmon before cleanup runs). Clear OUR name plus the legacy
|
|
# identities (the FreeToken-era frank-archon-qwen, the retired R9V
|
|
# container and the ad hoc experiment containers all hold this GPU); all
|
|
# idempotent.
|
|
for CTR in $FRANK_ARCHON_LEGACY_CONTAINERS "$FRANK_ARCHON_CONTAINER"; do
|
|
podman rm -f "$CTR" >/dev/null 2>&1 || true
|
|
done
|
|
|
|
LOG="${FRANK_ARCHON_LOG:-/home/dank/logs/frank_archon.log}"
|
|
mkdir -p "$(dirname "$LOG")"
|
|
|
|
# Publisher-vetted container contract (docs/DOCKER.md, compose/common.yaml):
|
|
# --network host (the server binds the host's addresses directly, no NAT),
|
|
# --init (the engine releases the cards on SIGTERM), seccomp=unconfined
|
|
# (Docker/podman's default profile refuses io_uring, which the n-gram
|
|
# table's reads go through, and the NUMA binding calls the ROCm runtime
|
|
# makes for host memory), memlock unbounded (the pinned ledger — legal
|
|
# because the root unit grants LimitMEMLOCK=infinity to this dank process),
|
|
# /dev/kfd + /dev/dri (render/video groups are moot for a root container).
|
|
# The template rides a single-file mount; the .rad dir is ro; /data holds
|
|
# the prefix-cache disk tier.
|
|
podman run -d --name "$FRANK_ARCHON_CONTAINER" \
|
|
--network host \
|
|
--init \
|
|
--security-opt seccomp=unconfined \
|
|
--ulimit memlock=-1:-1 \
|
|
--device /dev/kfd --device /dev/dri \
|
|
-v "$FRANK_ARCHON_MODEL_DIR":/models:ro \
|
|
-v "$FRANK_ARCHON_STATE_DIR":/data \
|
|
-v "$FRANK_ARCHON_STATE_DIR/tune":/opt/radiance/share/radiance/tune \
|
|
-v "$FRANK_ARCHON_TEMPLATE":/templates/template.jinja:ro \
|
|
"$FRANK_ARCHON_IMAGE" \
|
|
--model "/models/$FRANK_ARCHON_MODEL_FILE" \
|
|
--host :: --port "$FRANK_ARCHON_PORT" \
|
|
--served-model-name "$FRANK_ARCHON_SERVED_NAME" \
|
|
--override-chat-template /templates/template.jinja \
|
|
--tp "$FRANK_ARCHON_TP" --tp-wire "$FRANK_ARCHON_TP_WIRE" \
|
|
--max-num-seqs "$FRANK_ARCHON_MAX_SEQS" \
|
|
--max-model-len "$FRANK_ARCHON_MAX_MODEL_LEN" \
|
|
--placement "$FRANK_ARCHON_PLACEMENT" \
|
|
--host-pool-mib "$FRANK_ARCHON_HOST_POOL_MIB" \
|
|
--gpu-headroom-mib "$FRANK_ARCHON_GPU_HEADROOM_MIB" \
|
|
--vram-weights-mib "$FRANK_ARCHON_VRAM_WEIGHTS_MIB" \
|
|
--vram-kv-mib "$FRANK_ARCHON_VRAM_KV_MIB" \
|
|
--kv-cache-dtype "$FRANK_ARCHON_KV_DTYPE" \
|
|
--prefix-cache-host-mib "$FRANK_ARCHON_PREFIX_HOST_MIB" \
|
|
--prefix-cache-dir /data/kvcache/frank-archon \
|
|
--prefix-cache-disk-mib "$FRANK_ARCHON_PREFIX_DISK_MIB" \
|
|
--ngram-placement "$FRANK_ARCHON_NGRAM_PLACEMENT" \
|
|
--num-speculative-tokens "$FRANK_ARCHON_SPEC_TOKENS" \
|
|
--max-num-batched-tokens "$FRANK_ARCHON_MAX_BATCHED_TOKENS" \
|
|
${FRANK_ARCHON_EXTRA_ARGS:+$FRANK_ARCHON_EXTRA_ARGS} \
|
|
> "$LOG" 2>&1
|
|
|
|
# From here on, this script's lifetime IS the container's: wait returns the
|
|
# container's exit code, so a crash is a nonzero ExecStart and the unit's
|
|
# Restart=always is real. (systemd stop goes through ExecStop in the unit —
|
|
# podman wait alone cannot stop the container child.)
|
|
exec podman wait "$FRANK_ARCHON_CONTAINER"
|