Frank
a3e1c97408
The deployed unit failed its first boot with the engine core OOMing during profile/graph capture: "Tried to allocate 662.00 MiB. GPU 0 has a total capacity of 31.86 GiB of which 240.00 MiB is free ... try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True". The expert-offload plan fills VRAM to its modelled headroom by design, so the default allocator's fragmentation leaves the capture phase nothing — every successful bring-up probe (both scratch-port and 7770) carried this env, and the repo recipe dropped it. Also pins the seam: the setting is part of the qualified shape, not an optional tuning.
140 lines
6.8 KiB
Bash
Executable File
140 lines
6.8 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# serve-frank-primary.sh — frank-primary endpoint (tcclaviger RDNA4 vLLM fork,
|
|
# Intel/GLM-5.3-Flash-W4A16-AutoRound, 2x R9700, dankserver :7770).
|
|
#
|
|
# 2026-09-30 cutover from orcarouter Qwen3.8-Flash-Next-Uncensored-FP8 + MTP4.
|
|
# Rollback: commit 2339fae carries the whole pre-cutover scripts/ tree; restore
|
|
# it and deploy. The qwen payload and the R9V state dirs stay on disk.
|
|
#
|
|
# The engine is driven by `podman run` DIRECTLY: the image's entrypoint execs
|
|
# `vllm serve "$@"`, so the run line below IS the engine argv.
|
|
#
|
|
# Why this payload runs the offload path at all: 170 GiB of int4 experts cannot
|
|
# fit in 64 GiB of VRAM, so the engine keeps 12,096 experts per rank in pinned
|
|
# host memory and serves them through a 2,383-slot VRAM LRU arena. The MoE
|
|
# kernel is libr4d's grouped W4A16 GEMM (R4dW4a16MoEMethod), reached because the
|
|
# checkpoint's quant_method "auto-round" is overridden to "inc" by the fork.
|
|
#
|
|
# Shape: MAXLEN 131,072 x 2 seqs, bf16 KV, util 0.98, MTP OFF, prefetch OFF.
|
|
# Measured 2026-09-30: decode 9.9-10.0 tok/s, prefill 918 tok/s warm. The
|
|
# 35 tok/s target is NOT met — the bound is the fork's expert-gather read path
|
|
# (8.2 GB/s effective vs the link's 22.74 GB/s); see frank-primary.env and the
|
|
# runbook's arithmetic section.
|
|
#
|
|
# The root unit (scripts/frank-primary.service, User=dank,
|
|
# LimitMEMLOCK=infinity) grants the pin budget for the 73.64 GiB/rank of pinned
|
|
# host expert rows. A plain shell session also works, but the unit is the
|
|
# fleet-parity boot-persistent shape.
|
|
set -euo pipefail
|
|
|
|
SCRIPT_DIR="$(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}"
|
|
: "${FRANK_PRIMARY_NBATCH:?FRANK_PRIMARY_NBATCH must be set}"
|
|
: "${FRANK_PRIMARY_TOOLPARSER:?FRANK_PRIMARY_TOOLPARSER must be set}"
|
|
: "${FRANK_PRIMARY_REASONINGPARSER:?FRANK_PRIMARY_REASONINGPARSER must be set}"
|
|
# Capture podman's output BEFORE grepping: under `set -o pipefail`, the
|
|
# classic `podman images | grep -q` pattern races — grep exits on its first
|
|
# match, podman dies SIGPIPE (141) writing the remaining lines, and pipefail
|
|
# turns the 141 into "no match" (the 2026-09-30 deploy refusal).
|
|
DIGESTS="$(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 "$LOG")"
|
|
|
|
# --device /dev/dri is the WHOLE DIRECTORY (individual renderD nodes enumerate
|
|
# without the card nodes and HIP refuses contexts — "No CUDA GPUs are
|
|
# available" while device_count() says 2). --ipc=host for the engine's shared
|
|
# memory; memlock unbounded for the pinned host slabs.
|
|
# The entrypoint already execs `vllm serve "$@"`, 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 \
|
|
-e PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True \
|
|
-v "$FRANK_PRIMARY_MODEL_DIR":/models:ro \
|
|
"$FRANK_PRIMARY_IMAGE" /models \
|
|
--served-model-name "$FRANK_PRIMARY_SERVED_NAME" --port 7770 \
|
|
--tensor-parallel-size 2 \
|
|
--max-model-len "$FRANK_PRIMARY_MAXLEN" \
|
|
--max-num-seqs "$FRANK_PRIMARY_SEQS" \
|
|
--max-num-batched-tokens "$FRANK_PRIMARY_NBATCH" \
|
|
--gpu-memory-utilization "$FRANK_PRIMARY_UTIL" \
|
|
--enable-expert-offload \
|
|
--expert-precise-memory \
|
|
--enable-prefix-caching \
|
|
--enable-auto-tool-choice \
|
|
--tool-call-parser "$FRANK_PRIMARY_TOOLPARSER" \
|
|
--reasoning-parser "$FRANK_PRIMARY_REASONINGPARSER" \
|
|
--trust-remote-code \
|
|
> "$LOG" 2>&1
|
|
|
|
# NOT passed, deliberately (each measured on this payload — see the env file):
|
|
# --kv-cache-dtype fp8 disables the sparse MLA backend's rope-free
|
|
# Triton path, which is the only MLA decode on
|
|
# gfx12 (aiter's MLA op is gated on CDNA>2).
|
|
# --speculative-config MTP head loads and accepts well, but buys zero
|
|
# decode and collapses prefill on an
|
|
# offload-bound shape.
|
|
# --expert-prefetch* 36% precision; deleting it bought +40-51%.
|
|
# --kv-cache-memory-bytes the plan's own reserve covers this shape.
|
|
|
|
# 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"
|