# Quadlet unit: frank-medium replica A (rootless, boot-persistent).
#
# Install path on dankserver: ~/.config/containers/systemd/frank-medium-a.container
# Unit name: frank-medium-a.service (container name: frank-medium-a)
#
# WHY TWO REPLICAS INSTEAD OF TP=2. The intended shape for frank-medium is one
# tensor-parallel process across both R9700s (see frank-medium.container, kept
# as the target). That shape cannot run on this host: RCCL's collective kernels
# carry a hidden hostcall-buffer parameter, and the ROCr runtime refuses to
# dispatch them on a device without PCIe atomics ("Pcie atomics not enabled,
# hostcall not supported" -> AQL dispatch failed -> hipErrorIllegalState). The
# second R9700 sits behind the chipset bridges 05:00.0/06:09.0, which advertise
# `AtomicOpsCap: Routing-` — a read-only capability, so no software can enable
# atomics on that path; the amdgpu driver's pci_enable_atomic_ops_to_root()
# therefore fails for that GPU and KFD marks the CPU<->GPU2 link NO_ATOMICS.
# The first R9700 sits on CPU root port 00:01.1 (Routing+) and does have
# atomics. Result: every collective that touches GPU 2 dies at launch.
# Two independent single-GPU replicas use both cards instead; the proxy unit
# keeps the single :7770 endpoint. Full evidence: the frank-medium runbook.
#
# SHAPE. vLLM binds 0.0.0.0:7771 on the host network directly; no PublishPort.
# MAXLEN is 114688, not the TP=2 deployment's 262144: one card carries the
# whole model (~20 GiB of weights + drafter), leaving ~5.2 GiB of KV, and
# 131072 does not fit (measured: needs 5.58 GiB). KV_MEM=0 lets vLLM profile
# this shape instead of using the 2x7551-32624 pin, which is only valid at
# TP=2/262144.
#
# DEVICES. /dev/kfd + /dev/dri; HIP_VISIBLE_DEVICES=0 (the first R9700). The
# 2 GiB Raphael iGPU enumerates as index 2 and is excluded by the pin.
# Only HIP_VISIBLE_DEVICES is set, never ROCR_VISIBLE_DEVICES: ROCR filters
# first and HIP indexes into the filtered list, so a single-valued pair
# (ROCR=1,HIP=1) leaves an empty device set.
#
# 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).
[Unit]
Description=frank-medium replica A — vllm-radiance MXFP4 Qwen3.8-27B on R9700 #1
After=network-online.target

[Container]
ContainerName=frank-medium-a
Image=localhost/radiance-vllm:0.9.3
AddDevice=/dev/kfd
AddDevice=/dev/dri
GroupAdd=keep-groups
# The upstream launcher's exact podman posture (rootless).
PodmanArgs=--privileged --ipc=host --security-opt seccomp=unconfined --cap-add SYS_PTRACE --network=host
Environment=HIP_VISIBLE_DEVICES=0
Environment=SNAP=/models/Qwen3.8-27B-Uncensored-MXFP4-awq
Environment=DRAFTER=/models/Qwen3.8-27B-DFlash2-FP8
Environment=CHAT_TEMPLATE=/patches/qwen-fixed-v22.3.jinja
Environment=SERVED_NAMES=frank-medium
Environment=PORT=7771
Environment=TP=1
Environment=MAXSEQS=4
Environment=CHUNK=8192
Environment=MAXLEN=114688
Environment=GPU_UTIL=0.98
Environment=KV_MEM=0
Environment=SPEC_METHOD=dflash
Environment=SPEC=7
# Checkpoints (rw: nothing downloads at runtime, but vLLM mmaps the shards).
Volume=/home/dank/models:/models
# Tokenizer files ride the HF cache; HF_HUB_OFFLINE=1 is set in the entrypoint.
Volume=/home/dank/.cache/huggingface:/root/.cache/huggingface
# Compile cache. Shared with the other replica and with the TP=2 target: the
# entries are content-addressed, so shapes simply add subdirectories.
Volume=/home/dank/.radiance-cache-w4a8-093-gdnm-nqft-fp8s-gnq:/cache
# The pinned radiance clone: patches applied at every container start.
Volume=/home/dank/GitPackages/radiance-vllm-mxfp4:/patches:z
# The patched libr4d (pin b9e42ab + repo extras, key b9e42ab-rx6). The image's
# shipped r4d.so predates the GDN overflow fix and NaNs this model.
Volume=/home/dank/.cache/radiance-libr4d/b9e42ab-rx6:/r4d:z
# Entrypoint + healthcheck from this checkout, mounted read-only.
Volume=/home/dank/serverAppConfigs/dankserver/frank-medium/radiance-entrypoint.sh:/usr/local/bin/frank-medium-entrypoint.sh:ro
Volume=/home/dank/serverAppConfigs/dankserver/frank-medium/frank-medium-healthcheck.py:/usr/local/bin/frank-medium-healthcheck.py:ro
# The entrypoint must be the container command; the image's own entrypoint
# (which the patched script execs at the end) must not run unpatched.
PodmanArgs=--entrypoint /usr/local/bin/frank-medium-entrypoint.sh
# 200 only once the engine serves; during first-start compilation the
# container is legitimately unhealthy. HealthCmd is split on spaces into an
# argv array by the podman 5.x v1 generator, hence the file-based probe.
HealthCmd=python3 /usr/local/bin/frank-medium-healthcheck.py
HealthInterval=60s
HealthTimeout=30s
HealthRetries=3
HealthStartPeriod=1800s
Pull=never

[Service]
# First start compiles Triton/inductor kernels (several minutes) before the
# engine loads ~20 GiB of weights.
TimeoutStartSec=1800
Restart=on-failure
RestartSec=10

[Install]
WantedBy=default.target