serverAppConfigs/scripts/serve-frank-primary.sh

#!/usr/bin/env bash
# serve-frank-primary.sh — frank-primary endpoint (tcclaviger RDNA4 vLLM fork,
# orcarouter Qwen3.8-Flash-Next-Uncensored-FP8, 2x R9700,
# dankserver :7770; 2026-09-29 cutover from the R9V radiance fork — git tag
# frank-primary-r9v-q8-20260929 is the pre-cutover state).
#
# The engine is driven by `podman run` DIRECTLY: the image's entrypoint execs
# `vllm serve "$@"`, so the run line below IS the engine argv. This replaces
# the R9V launcher/shim machinery (that fork needed a docker->podman shim and
# a 104-key on-host setup state; this stack is fully expressed by flags, and
# every flag here was qualified by boot probe on 2026-09-29 — see
# frank-primary.env for the qualification record).
#
# Shape (2026-10-02 shape E): MAXLEN 200704 x 3 slots, fp8 KV, KV_BYTES
# 3,150,000,000 PER RANK — the POOL, not the slot count, caps resident
# conversations at ~2 full-length (measured: 398,658 tokens = 1.99x);
# shorter requests use the spare blocks. --max-num-seqs stays 3 because SEQS=2
# CANNOT boot this model
# (torch.fx ConstraintViolationError on query_start_loc, measured at both
# MNBT 1024 and 2048 — the 2x2 lives in frank-primary.env). NO speculative
# decode, --max-num-batched-tokens 1024 (Frank's lock), MoE gather geometry
# R4D_LRU_GATHER_CHUNKS=32 / R4D_LRU_GATHER_LANES=64 (+18.7% decode, grows
# with depth), prefix caching, expert prefetch OFF (36% precision measured),
# TunableOp off. Shape E adds --expert-precise-memory (fitted 5.25 GiB overhead
# instead of the 7.60 GiB default -> expert arena 17.22 GiB / 7,522 slots, +16%)
# and GPU_MAX_HW_QUEUES=2. The native-262144 and fp8+MTP4 shapes are retired to
# git tag frank-primary-fp8-mtp-20261001.
#
# THE COMPILE CACHE IS MOUNTED, and that is a boot-cost fix, not a tuning knob:
# the image ships no /root/.cache at all, our first boot writes 1.1 GB of vLLM
# AOT/torch_compile artifacts plus 229 MB of comgr JIT kernels into the
# container's ephemeral layer, and `podman rm -f` deletes them — so every
# deploy/restart/reboot re-pays `torch.compile took 181.20 s in total` (173.19 s
# of it one graph). Mounting FRANK_PRIMARY_CACHE_DIR at /root/.cache makes all
# later boots load the compiled artifact instead, and hides nothing.
#
# The root unit (scripts/frank-primary.service, User=dank,
# LimitMEMLOCK=infinity) grants the pin budget for the tiered-expert host
# slabs (~20.5 GiB/rank of pinned anonymous memory). A plain shell session
# also works, but the unit is the fleet-parity boot-persistent shape.
set -euo pipefail

SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
ENV_FILE="${FRANK_PRIMARY_ENV_FILE:-$SCRIPT_DIR/frank-primary.env}"

if [ ! -f "$ENV_FILE" ]; then
    echo "serve-frank-primary: env file missing: $ENV_FILE" >&2
    exit 1
fi
set -a
# shellcheck disable=SC1090
source "$ENV_FILE"
set +a

: "${FRANK_PRIMARY_IMAGE:?FRANK_PRIMARY_IMAGE must name the digest-pinned image}"
: "${FRANK_PRIMARY_MODEL_DIR:?FRANK_PRIMARY_MODEL_DIR must name the FP8 payload}"
: "${FRANK_PRIMARY_MODEL_SHARDS:?FRANK_PRIMARY_MODEL_SHARDS must give the shard count}"
: "${FRANK_PRIMARY_CONTAINER:?FRANK_PRIMARY_CONTAINER must name the container}"
: "${FRANK_PRIMARY_SERVED_NAME:?FRANK_PRIMARY_SERVED_NAME must name the alias}"
: "${FRANK_PRIMARY_PUBLISH:?FRANK_PRIMARY_PUBLISH must be host:container}"
: "${FRANK_PRIMARY_MAXLEN:?FRANK_PRIMARY_MAXLEN must be set}"
: "${FRANK_PRIMARY_SEQS:?FRANK_PRIMARY_SEQS must be set}"
: "${FRANK_PRIMARY_KV_BYTES:?FRANK_PRIMARY_KV_BYTES must be set (PER RANK)}"
: "${FRANK_PRIMARY_KV_DTYPE:?FRANK_PRIMARY_KV_DTYPE must be set (auto = bf16 KV)}"
: "${FRANK_PRIMARY_REASONING_PARSER:?FRANK_PRIMARY_REASONING_PARSER must be set (qwen3)}"
: "${FRANK_PRIMARY_TOOL_PARSER:?FRANK_PRIMARY_TOOL_PARSER must be set (qwen3_xml)}"
: "${FRANK_PRIMARY_CHAT_TEMPLATE_KWARGS:?FRANK_PRIMARY_CHAT_TEMPLATE_KWARGS must be set}"
# Capture podman's output BEFORE grepping: under `set -o pipefail`, the
# classic `podman images | grep -q` pattern races — grep exits on its first
# match, podman dies SIGPIPE (141) writing the remaining lines, and pipefail
# turns the 141 into "no match" (the 2026-09-30 deploy refusal).
DIGESTS="$(podman images --format '{{.RepoDigests}}')"
if ! grep -qF "${FRANK_PRIMARY_IMAGE#*@}" <<<"$DIGESTS"; then
    echo "serve-frank-primary: pinned image absent from rootless storage: $FRANK_PRIMARY_IMAGE" >&2
    echo "  fetch it: podman pull $FRANK_PRIMARY_IMAGE" >&2
    exit 1
fi

if [ ! -f "$FRANK_PRIMARY_MODEL_DIR/config.json" ]; then
    echo "serve-frank-primary: payload config missing: $FRANK_PRIMARY_MODEL_DIR/config.json" >&2
    exit 1
fi
SHARDS="$(find "$FRANK_PRIMARY_MODEL_DIR" -maxdepth 1 -name 'model-*-of-*.safetensors' | wc -l)"
if [ "$SHARDS" != "$FRANK_PRIMARY_MODEL_SHARDS" ]; then
    echo "serve-frank-primary: payload shard count wrong: $FRANK_PRIMARY_MODEL_DIR" >&2
    echo "  found $SHARDS safetensors, want $FRANK_PRIMARY_MODEL_SHARDS" >&2
    echo "  re-fetch: scripts/download-frank-primary.sh" >&2
    exit 1
fi
if [ ! -f "$FRANK_PRIMARY_MODEL_DIR/model.safetensors.index.json" ]; then
    echo "serve-frank-primary: weight-map index missing: $FRANK_PRIMARY_MODEL_DIR/model.safetensors.index.json" >&2
    exit 1
fi

if [ ! -e /dev/kfd ] || [ ! -d /dev/dri ]; then
    echo "serve-frank-primary: GPU device nodes absent (/dev/kfd, /dev/dri)" >&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 retired R9V container and the ad hoc experiment container
# both hold these GPUs); all idempotent.
for CTR in $FRANK_PRIMARY_LEGACY_CONTAINERS "$FRANK_PRIMARY_CONTAINER"; do
    podman rm -f "$CTR" >/dev/null 2>&1 || true
done

LOG=/home/dank/logs/frank_primary.log
mkdir -p "$(dirname "$LOG")"

# Persistent compile cache (see the header). Create it before the mount so even
# the first, cold boot has a target; unset -> no mount, exactly the old
# ephemeral behaviour. It carries /root/.cache/vllm (AOT + torch_compile) and
# /root/.cache/comgr (HIP kernel JIT).
CACHE_DIR="${FRANK_PRIMARY_CACHE_DIR:-}"
if [ -n "$CACHE_DIR" ]; then
    mkdir -p "$CACHE_DIR"
fi

# --device /dev/dri is the WHOLE DIRECTORY (individual renderD nodes enumerate
# without the card nodes and HIP refuses contexts — "No CUDA GPUs are
# available" while device_count() says 2). --ipc=host for the engine's shared
# memory; memlock unbounded for the pinned host slabs.
# The entrypoint already execs `vllm serve "$@"`, so no `serve` here.
podman run -d --name "$FRANK_PRIMARY_CONTAINER" \
  --publish "$FRANK_PRIMARY_PUBLISH" \
  --ipc=host --ulimit memlock=-1:-1 \
  --cap-add SYS_PTRACE \
  --device /dev/kfd --device /dev/dri --device /dev/mem \
  -e HIP_VISIBLE_DEVICES=0,1 -e VLLM_ROCM_USE_AITER=0 \
  ${FRANK_PRIMARY_GPU_MAX_HW_QUEUES:+-e GPU_MAX_HW_QUEUES="$FRANK_PRIMARY_GPU_MAX_HW_QUEUES"} \
  ${FRANK_PRIMARY_GATHER_CHUNKS:+-e R4D_LRU_GATHER_CHUNKS="$FRANK_PRIMARY_GATHER_CHUNKS"} \
  ${FRANK_PRIMARY_GATHER_LANES:+-e R4D_LRU_GATHER_LANES="$FRANK_PRIMARY_GATHER_LANES"} \
  ${CACHE_DIR:+-v "$CACHE_DIR":/root/.cache} \
  -v "$FRANK_PRIMARY_MODEL_DIR":/models:ro \
  "$FRANK_PRIMARY_IMAGE" /models \
  --served-model-name "$FRANK_PRIMARY_SERVED_NAME" --port 7770 \
  --tensor-parallel-size 2 \
  ${FRANK_PRIMARY_DCP:+--decode-context-parallel-size "$FRANK_PRIMARY_DCP"} \
  --max-model-len "$FRANK_PRIMARY_MAXLEN" \
  --max-num-seqs "$FRANK_PRIMARY_SEQS" \
  ${FRANK_PRIMARY_MNBT:+--max-num-batched-tokens "$FRANK_PRIMARY_MNBT"} \
  ${FRANK_PRIMARY_PRECISE_MEMORY:+--expert-precise-memory} \
  --gpu-memory-utilization "$FRANK_PRIMARY_UTIL" \
  --kv-cache-memory-bytes "$FRANK_PRIMARY_KV_BYTES" \
  --kv-cache-dtype "$FRANK_PRIMARY_KV_DTYPE" \
  --enable-prefix-caching \
  --enable-auto-tool-choice --tool-call-parser "$FRANK_PRIMARY_TOOL_PARSER" \
  --reasoning-parser "$FRANK_PRIMARY_REASONING_PARSER" \
  --default-chat-template-kwargs "$FRANK_PRIMARY_CHAT_TEMPLATE_KWARGS" \
  --trust-remote-code \
  > "$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=on-failure is real. (systemd stop goes through ExecStop in the
# unit — podman wait alone cannot stop the container child.)
exec podman wait "$FRANK_PRIMARY_CONTAINER"