Frank
4fca739bf8
The radiance MXFP4 stack cannot run TP=2 on this host. RCCL's collective
kernels carry a hidden hostcall-buffer parameter, and ROCr refuses to
dispatch them on a device without PCIe atomics: the AQL dispatch fails with
hipErrorIllegalState ("the operation cannot be performed in the present
state"), which is what every two-rank collective hit. 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
atomic routing on that path and the driver's
pci_enable_atomic_ops_to_root() fails for that card. The first card, on CPU
root port 00:01.1, has atomics enabled.
Ruled out: kernel version (7.0.0-28/-30/-31 identical, after a full upgrade),
iommu=pt, P2P hardware (45.3 GB/s between the cards), the shipped librccl (a
from-source rebuild reproduces the failure at the same call path), vLLM and
pynccl (a bare two-rank torch.distributed allreduce fails the same way), all
NCCL transport knobs, and single-rank tests (NCCL short-circuits at
world_size=1, so one-card success proves nothing).
Deployment: three rootless Quadlets — frank-medium-a (:7771, card 1),
frank-medium-b (:7772, card 2), both TP=1 at 114688 context (262144 and
131072 do not fit one card's KV) with vLLM-profiled KV — and
frank-medium-proxy (:7770), a round-robin that preserves the fleet contract
of one endpoint and one served model name. frank-medium.container stays as
the TP=2 target for a host whose second card is atomic-capable; the deploy
handler does not install it and trashes any stale copy.
Measured through the proxy (vllm bench serve, random dataset, --ignore-eos):
conc 1 42.8 tok/s, conc 4 147.6 tok/s, conc 8 230.8 tok/s, 32k prefill at
~2.8k tok/s per card, TPOT p50 23.6-28.8 ms.
Also: healthcheck reads PORT so one probe serves all three units, the hermes
example and the harness models.yml drop to the real 114688 context, and the
runbook records the full evidence chain.
53 lines
2.3 KiB
INI
53 lines
2.3 KiB
INI
# Quadlet unit: frank-medium proxy (rootless, boot-persistent).
|
|
#
|
|
# Install path on dankserver: ~/.config/containers/systemd/frank-medium-proxy.container
|
|
# Unit name: frank-medium-proxy.service (container name: frank-medium-proxy)
|
|
#
|
|
# WHAT IT IS. A round-robin reverse proxy in front of the two single-GPU
|
|
# frank-medium replicas (:7771 on R9700 #1, :7772 on R9700 #2). It preserves
|
|
# the fleet contract: one endpoint on host port 7770 answering as the served
|
|
# model name frank-medium, OpenAI /v1, streaming included.
|
|
#
|
|
# WHY IT EXISTS. TP=2 — one vLLM process spanning both cards — is impossible
|
|
# on this host (see frank-medium-a.container and the runbook: RCCL's kernels
|
|
# need PCIe atomics, and the second card's chipset path advertises
|
|
# AtomicOpsCap: Routing-). Two replicas are how both cards get used.
|
|
#
|
|
# ROUTING. vLLM's OpenAI API is stateless per request, so round-robin is
|
|
# sound; there is no session affinity to preserve. /health answers 200 while
|
|
# at least one replica is up and names the ones that are down. The proxy runs
|
|
# on host networking so it can bind 7770 and reach the replicas on loopback.
|
|
#
|
|
# The script is a few dozen lines of aiohttp, mounted read-only out of
|
|
# /home/dank/serverAppConfigs (deploy.sh pulls that checkout before dispatch).
|
|
# It reuses the same image as the replicas: aiohttp is already there and no
|
|
# extra image has to be pulled on this host.
|
|
[Unit]
|
|
Description=frank-medium proxy — round-robin in front of the two single-GPU replicas
|
|
After=network-online.target
|
|
Wants=frank-medium-a.service frank-medium-b.service
|
|
After=frank-medium-a.service frank-medium-b.service
|
|
|
|
[Container]
|
|
ContainerName=frank-medium-proxy
|
|
Image=localhost/radiance-vllm:0.9.3
|
|
PodmanArgs=--network=host
|
|
Environment=PORT=7770
|
|
Environment=UPSTREAMS=http://127.0.0.1:7771,http://127.0.0.1:7772
|
|
Volume=/home/dank/serverAppConfigs/dankserver/frank-medium/proxy/roundrobin-proxy.py:/usr/local/bin/roundrobin-proxy.py:ro
|
|
Volume=/home/dank/serverAppConfigs/dankserver/frank-medium/frank-medium-healthcheck.py:/usr/local/bin/frank-medium-healthcheck.py:ro
|
|
PodmanArgs=--entrypoint /usr/local/bin/roundrobin-proxy.py
|
|
HealthCmd=python3 /usr/local/bin/frank-medium-healthcheck.py
|
|
HealthInterval=60s
|
|
HealthTimeout=30s
|
|
HealthRetries=3
|
|
HealthStartPeriod=60s
|
|
Pull=never
|
|
|
|
[Service]
|
|
Restart=on-failure
|
|
RestartSec=10
|
|
|
|
[Install]
|
|
WantedBy=default.target
|