internal/control/slurmsvc tells each node what it is, writes slurm.conf
and gres.conf from the nodes' reports and the inventory, and moves each node
of slurm.nodes between llmgw and Slurm: lent, drained of replicas first, then
resumed in Slurm; taken back, drained in Slurm and cordoned in llmgw until
its last job step ends. Kept every tick from the settings and the agents'
reports, so a new leader carries on. A broken Slurm never keeps a node from
llmgw. GET /api/v1/slurm; ctl slurm status, setup, lend, reclaim, off.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A Slurm message says whether the node runs slurmctld on the leader's files,
slurmd configless, both or neither, and whether it is lent. The agent
installs munge and Slurm from the machine's sources (22.05 or newer, for
cgroup v2), writes the munge key, starts slurmd through a drop-in with
--conf-server, resumes a lent node that llmgw drained and drains one that is
not, never touching a drain a Slurm administrator made, and reports its
version, slurmd -C, state and jobs in SlurmStatus. Told it has no part, it
stops what it started. New nodes enter slurm.conf drained.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Each agent measures one core's memory rate beside the whole machine's; the
estimate takes a replica's threads at about one core's rate each, up to the
machine's, calibrated by llama-bench on the PoC. The serve form shows it
beside a card's, warns when slow, and asks for the CPU on purpose when a
reply would take minutes; ctl model plan, the console and serve jobs say
it too.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The busy figure is nvidia-smi's utilization.gpu: the share of time any
kernel ran, which a kernel on one SM fills. On cuda01 decode read 92% busy
while the SMs had work 69% of the time and issued on 18% of their cycles.
Busy is now said to be that, and beside it: each card's draw against its
power limit (efficiency table, fleet and node charts, the console's GPU
work chart), and where the profiling counters can be read, SMs active, SM
occupancy, tensor cores and DRAM (llmgw_gpu_*_active_percent), from NVML's
GPM on Hopper and later or a dcgm-exporter on the node
(discovery.dcgm_exporter). The GPU map colours by work by default and keeps
busy as a mode. A MIG instance is never published with its card's profile.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
At the user's asking: we know what a card's link could be, so a card
linked slower is reported. Each agent reads, apart from the GPU query so
that a driver not knowing a field costs nothing else, the fastest PCIe
generation card and slot allow together, the card's own, and the lanes in
use and the card's most (nvidia-smi; NVML in the nvml build). The current
generation is not compared: it drops while a card idles. A card on fewer
lanes, or a slot of an older generation, is a node warning with the GB/s
it carries against what it could — on the dashboard, the console and in
llmgw doctor, which points at lspci's LnkCap and LnkSta. MIG instances are
said of their card. GPU proto fields 23-26.
The PoC's Quadro RTX 6000 reads Gen3 of Gen3, x16 of x16, idle at Gen1:
nothing to say.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Measuring it in the startup scan held every agent half a second or more
before registering, which on a shared CI runner was past the failover
tests' wait. Now it runs once a process, in the background, the first time
it is asked for, and Heartbeat.mem_bandwidth_gbs carries it when known;
the control plane keeps the last figure and a heartbeat without one leaves
it. The agent's tests do not measure.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Each agent measures its node's memory read rate when it starts: every CPU
sums a share of a buffer past any cache, a tenth of free memory at most,
the best of four passes, in a fraction of a second; reported in Host
(mem_bandwidth_gbs) and NodeView. A token on a CPU reads every weight it
uses once, so one reply's speed is about that rate over those bytes:
modelplan.CPUTokensPerSecond, 0.68 of the measured rate plus 5 ms a token,
calibrated on the PoC against llama.cpp's predicted_per_second (node01
24.9 GB/s, qwen2.5-1.5b: 14.5 measured, 14.7 estimated; node05 41.9 GB/s,
qwen2.5-14b: 3.3 and 3.2). A model of experts named …-A3B reads its active
part (ActiveShare).
The explorer shows it as CPU tok/s, at Q4_K_M on the fastest node that
holds the model; a repository's page gives it for each GGUF by its size.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Python pickles (.bin, .pt, .pth, .ckpt, .pkl) run whatever they hold when
loaded, as the engine's user, on the node; that is how the malicious models
found on Hugging Face work. The node refuses such a source, or a mirror set
holding one, before fetching anything. A model added with one, or given
one, is refused, while one already in the catalog still loads and is
refused by its node with the same words. vLLM and SGLang downloading a
model by its id get --load-format safetensors. The mirror page marks the
file. allow_pickle: true on a model lets it through on purpose, carried to
the node in EngineProfile.allow_pickle.
BACKLOG M lists the rest: checksums against Hugging Face on every path,
its own scan, trusted publishers, engines without the internet, an eval
before an untrusted model serves.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A job names the catalog model the adapter is for, the safetensors weights to
train on, the node and the MiB of a card it needs, and question/answer pairs.
The control plane sends it when the node's agent is there and nothing else
trains on it; the agent trains with its installed vLLM's torch and a pinned
overlay of peft and accelerate (no second environment), as the engines'
user, on the card with that much free — beside an engine, if it leaves that
much — converts the adapter to GGUF with the installed llama.cpp's own
conversion code when the model is served by llama.cpp, and sends what it
made back in pieces, kept in the store to download. Progress, loss and peak
card memory are reported as it goes; a node that goes fails its job.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
agents.default and agents.nodes.<id> in the cluster's settings hold
everything agent.yaml can say but the agent's id, control planes, address and
certificate, which stay in the file and are refused there. The control plane
sends each node its settings on register and, a second apart, when they
change; an agent whose settings changed checks they load beside its file,
keeps them and starts again on them, engines serving throughout. An edited
agent.yaml that loads restarts the agent too. History, audit, ctl config, the
console and the portal's settings page cover them as the rest of the
settings.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Issue #3 asked for commands to stop and start the system, and 05aa21c gave
only one machine's services. Now:
- llmgw stop sets serving.stopped in the cluster's settings, live: the
reconciler wants every model at no replicas, freeing every GPU, and the
gateway answers every POST under /v1/ with 503 system_stopped. The control
planes, agents and mirror keep running, and no model's definition changes.
- llmgw start clears it; every model is placed again as it asks.
- llmgw restart has every agent restart over its stream (RestartAgent), then
the other control planes over ssh, standbys before a leader, then this
one; engines keep serving.
- llmgw status is the cluster's summary, saying when it is stopped.
One machine's services moved to llmgw service status|start|stop|restart.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
It was sent once, with READY, and kept only in the leader's memory: a
failover or an agent restart lost it. The agent now keeps it with the
shard's state on disk (ShardSpec.Compute, set by Supervisor.SetCompute) and
reports it with each running shard when it registers (RunningShard.compute),
which adoption carries onto the replica.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
llama.cpp's start-up output is read as a shard becomes ready: the devices it
used, its backend, and the layers it offloaded. That goes up with READY in a
new ShardStatus.compute, is kept on the shard, and is shown by the admin
API, ctl replicas (ON) and the console (COMPUTE). A shard given GPUs whose
engine says it found no usable GPU or offloaded no layer is stopped and
failed, even where nvidia-smi cannot be asked.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
firewall.enabled (default true) is a cluster setting, applied live: the
leader sends a Firewall message to every agent when it registers and when
the setting or firewall_networks changes, and the agent (root) takes llmgw's
nft table out or installs it. A control plane writes the state to
/var/lib/llmgw/firewall.json, which llmgw-firewall-sync.path applies as root
with `llmgw firewall sync`; server init and server add install the units,
`llmgw firewall sync --install` on one set up before. node add and server
add put no firewall on a machine while the setting is off.
`llmgw wipe` removes llmgw from a machine after listing what goes and asking
for its name: units, engines' processes, the nft table, /etc/llmgw,
/var/lib/llmgw, the agent's state, the sudo grant, the CA from the trust
store, keepalived's configuration when llmgw wrote it, and the users.
--models, --store (Patroni member, etcd, or the local database) and --all
take more. The console has it under Do.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Conflicts with the LoRA work: vLLM's arguments, the engine profile, router
metrics and the scheduler's request all keep both; agent.pb.go regenerated
from the merged proto; the two test fakes of vLLM given separate names.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Plan §7.5 tier 2, opt-in per profile with kv_events. The agent starts vLLM
publishing KV cache events to a loopback port it listens on (pure-Go zmq4,
msgpack in both of vLLM's encodings), with sha256_cbor hashing and a fixed
PYTHONHASHSEED; it mirrors each engine's blocks and sends net changes up the
existing stream, with a full copy on every new one and a reset on gaps,
restarts and clears. The control plane hands them to the router, for the
sending node's own replicas only. The router tokenizes through a replica's
/tokenize, hashes the tokens as vLLM does (checked against cbor2/hashlib
golden values), and scores replicas by the share of leading blocks held,
falling back to the approximate tree. New metrics beside
llmgw_prefix_decisions_total. Untested against a running vLLM.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Conflicts: server.go imports (both kept); agent.pb.go regenerated with buf
from the merged proto.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
A bundle carries what a cluster would download — llmgw's release with its
signed checksums, every llama.cpp build per architecture with GitHub's
checksums, model files pinned and checked against Hugging Face's — into a
directory or a tar whose manifest sha256 is carried apart. Import checks
everything, the release against the signing key, before anything is put in
the mirror. With offline.mirror set, nodes install llama.cpp from the
mirror against checksums the control plane holds and sends over the agent
stream; releases default to the mirror for node add, ctl upgrade and agent
upgrades. server init and the setup form install from a bundle.
The Helm chart runs one control plane with SQLite on a claim or an external
PostgreSQL, Secrets for the agent certificate and admin token, Services,
Ingress and ServiceMonitor; deploy/container/Dockerfile builds its image.
GPU nodes stay outside Kubernetes, as docs/kubernetes.md explains.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Conflicts: config imports and docgen sources (both kept); agent.pb.go
regenerated with buf from the merged proto (MIG devices and trace context).
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
A reconcile pass that does something is a trace, with placement (where it
went, or every candidate turned down), scale-up/down, drain, stop, eviction,
preemption, reaping and restarts beneath it. A replica's start is a span open
from placement until it serves; the start command carries its context in a
new ControlMessage.trace field, and the agent continues the trace through
the weights fetch, engine launch, rendezvous and readiness wait. Stops,
drains, adoption and engine installs are traced on the node, model jobs are
a trace with a span per step linked to the replica's start, and agent.yaml
takes the same tracing block as server.yaml. Off, every span is the no-op one
and commands carry nothing.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Discovery reports a card in MIG mode as its instances instead of the whole
card, on both paths: nvidia-smi (-L names them, -q -x gives their memory,
ids and processes) and NVML (GetMigMode, GetMaxMigDeviceCount,
GetMigDeviceHandleByIndex, behind an interface so it is tested with a fake).
Each instance has its MIG UUID, its own memory, and a class from the card's
and the profile: a100-80g-mig-3g.40gb. Placement numbers instances
1000 + 100 x card + instance and every view shows them as card/migN.
A replica on MIG runs on exactly one instance: a process opens one MIG
device and instances have no NVLink between them, so tp, pp, gpus or nodes
above one on a MIG class are refused in catalog validation and again in
placement, and the planner offers one instance or none. The agent gives
the engine CUDA_VISIBLE_DEVICES=MIG-<uuid> (no Vulkan device variable on
MIG). Memory and processes are per instance; heat, power and wear the
card's; utilisation is left out rather than reported as zero. A card in MIG
mode with nothing carved stays out of placement with the reason, and
llmgw doctor reports each card's mode and instances and warns of the states
in which nothing can run. ctl nodes, ctl status, the console and the plan
count devices by class. docs/install.md has a MIG section.
Written against fakes of nvidia-smi and NVML output; not yet run on MIG
hardware.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
server add gives another machine this llmgw, a certificate, the
configuration and store address, lets it into the store through Patroni, and
starts it; --vip keeps a floating address on the leader with keepalived,
following a new /leader endpoint. Nodes learn every control plane from the
leader and notice a dead one by HTTP/2 ping instead of after the kernel's
fifteen minutes. The setup, console, node and init screens are drawn full
screen in one frame: title bar, sidebar, bordered panel, key bar, dialogs.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
A card with something else on it when the agent started stayed out of
placement after that process let go of it, until the agent restarted. The
agent now sends what processes other than its own engines hold on each card,
and the control plane replaces the registration verdict with it.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Every minute the agent reads nvidia-smi's full report, its NVLink error
counters and the kernel's XID lines. They are published per card,
shown on the node page and the GPU map, charted in Grafana, and five
alerts watch them.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
They were read once, at agent start, and published unchanged since.
Each sample now carries utilisation, memory and bandwidth in use, the SM
clock and uncorrected ECC errors. The node page charts each card, the
cluster page the fleet by class, Grafana has a GPU row, and three GPU
alerts are added.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
A node that cannot run the CUDA 13 build installs the same version's
CUDA 12.9 build from vLLM's GitHub release, with PyTorch's cu129 torch;
the install computes on the GPU before it counts. The build can be
chosen per node — auto, cu13, cu129, none — on the cluster page, with
ctl engine-build, or over the admin API; the control plane keeps the
choice and tells the node at once.
Refs #2.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
A model's adapters are fetched by each node with its weights and loaded
unapplied at start; a request naming an adapter reaches the model's
replicas with llama.cpp's per-request lora field. Adapter names share the
model namespace, are listed, and follow allowlists on their own. The
router's config seed and pushed catalog now build the name map in one place.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Every agent samples, at most every ten seconds: nvidia-smi's temperature,
HBM temperature, power draw, enforced limit and throttle reasons per GPU;
hwmon's CPU package and board inlet temperatures; and CPU package power
from RAPL's energy counters. Sent with heartbeats, published as metrics
and shown on the node page; unmeasured sensors are absent, never zero.
Observe-only, step 0 of docs/facility-aware-placement.md, which now
describes the agent source and what these readings can and cannot say.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
A profile's cpu_cores is reserved out of its node's CPUs by placement, as
memory is, and becomes the engine's thread count. Agents report their CPU
count in registration and heartbeats. New CPU models must declare memory;
model views show reserved against measured memory with warnings, and
ctl model resources sets both for a stored model.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Every upgrade so far has been a script of mine copying a binary to each
machine over ssh, restarting it and polling until it came back — which is
the job, but not something the product could do, and which needed ssh into
every node.
`sudo llmgw ctl upgrade VERSION` on the control plane does it. This machine
first: the release for its platform, checked against the release's
checksums, the old binary kept beside it, llmgw-server restarted, and a wait
until every node that was ready has reconnected. Then each node in turn: the
control plane tells its agent the version over the stream it already holds;
the agent fetches and checks the release itself, swaps it in with a rename,
answers, and exits with status 75 so systemd starts the new binary. Engines
keep running, as for any agent restart, and are adopted again.
A node is done when it is back on the new version, ready, with as many ready
replicas as before; one that is not within the timeout stops the run before
the next node, so a bad release reaches one machine. Nodes already on the
version are skipped, so running it again resumes.
The fetch-and-verify is one package now, shared with onboarding's idea of
what a release version looks like.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Engines listen on every address their node has, with no key. Checked on the
live cluster: from a neighbouring node, a request straight to an engine's
port was answered — past the gateway's authentication, quotas and
accounting, by anyone who could reach the node.
Each replica's engine is now started with a key and refuses requests without
it. The key is derived from the replica id with an HMAC over a secret kept
in the store, rather than stored per replica: the router has to send the
right key to replicas this process never started — adopted after a restart,
or placed by the other control plane — and a function of a shared secret
gives that without a table to keep in step. A key taken from one node opens
that replica only. The secret is made on first use and copied with the rest
of the store when moving to PostgreSQL; a new one would lock the router out
of every running engine at the moment of the move.
The key reaches llama.cpp and vLLM through their environment
(LLAMA_API_KEY, VLLM_API_KEY) rather than their command line, which every
user on the node can read; SGLang only takes it as an argument. The agent's
readiness check, the router's proxy and its metrics scrape send it, the
client's own Authorization still never reaches the engine, and `ctl bench`
fetches the key of the replica it is pointed at from the admin API.
Engines started before this keep running without a key until their replica
is next started. With no store there is nowhere to keep the secret, and
engines start without one, with a warning.
Also formats two files that went in unformatted.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
doctor checks a node alone, and every check can pass while two nodes still
cannot reach each other. ctl fabric-test A B asks B's agent for an
ib_write_bw server and A's for the client, adapter by adapter as NCCL pairs
them, one rail at a time, and grades each against its link's rate. It goes
through the agents' streams, so there is no SSH between nodes; the agent
installs perftest the first time, and names the RoCE v2 GID itself.
The result is read from perftest's table by its heading, not a column
number. Agents now list the requests they answer beyond the usual
(Register.features), and the control plane refuses a test on one too old to
answer instead of waiting minutes for it. The forwarding dispatcher carries
the new capability, and its test says so: a missing forward would have made
the command quietly unavailable in production.
Not yet run over real InfiniBand or RoCE; this cluster has neither.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
A control plane of this release asks every node for vLLM. An agent of the
last one does not know how to install it, and answered "unsupported", so a
cluster half way through its upgrade showed every node as failing. Agents
now say which engines they can install (Register.installable_engines), and
are asked for no others; an agent that says nothing is asked for llama.cpp
alone, as it always was.
doctor reports the CPU's vector extensions, and warns when AVX2 is missing,
with the fix for a VM: the test node for node add was one, on QEMU's default
CPU model, where llama.cpp runs several times slower and nothing else looks
wrong. node add shows it, since it runs doctor.
The changelog's unreleased section was two releases' worth of sections one
after the other, with two lists of fixes and the upgrade notes in the
middle. It is one entry now: largest changes first, the fixes together, and
every upgrade note at the end, with vLLM's default install and how to keep
your own.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
A GB200 NVL72 rack or an NVLink Switch system is a scale-up island: its
GPUs reach each other over NVLink whatever node they are in. Each GPU
now reports its fabric from nvidia-smi -q - state, status, ClusterUUID,
CliqueId, bandwidth - at registration and once a minute after, since a
fabric manager restarting drops every card out at once; and each node
reports nvidia-imex and its channels, without which the domain's GPUs
cannot share memory across nodes. A single machine's NVSwitch, which
reports a cluster of zeros, is no domain.
A replica spanning nodes is placed inside one domain first, on nodes
whose every card is joined and whose IMEX is up, and its shards are
told NCCL_MNNVL_ENABLE=1; InfiniBand is the fallback.
/admin/nvlink draws each domain as a rack - the NVLink Switch band on
top, light running down a backplane, trays of GPU chips that glow when
joined, pulse red when not, turn amber on degraded bandwidth - and
lists what keeps a tray out. A node's page shows its GPU-by-GPU NVLink
matrix, each card's NUMA node and nearest adapter, and its domain and
IMEX. doctor checks joining, bandwidth, IMEX and its channel; metrics
llmgw_gpu_nvlink_joined and llmgw_imex_up; /api/v1/nvlink.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
The control plane asks one node on each physical fabric to run
ibnetdiscover every five minutes and parses the text itself, so a
format the parser has not met is a control plane upgrade, not one on
every node. From the map it works out the switch tiers (leaf, spine,
core, by distance from the adapters), which adapter is which node's,
which cables trained below the rate the rest of their kind run at, and
whether the rails line up: every node's Nth adapter on its own leaf.
A page per fabric (/admin/fabrics) draws it: switches in their tiers,
adapters fanned out under their leaves, cables coloured by rate and
bundled, degraded ones marching red with a marker, and the cluster's
own adapters live - down ports glowing red, and particles running each
cable as fast as its adapter is sending and receiving, from the
counters. It zooms, pans, fades what a hovered switch or adapter does
not touch, opens a panel of detail on a click, colours by rail, finds a
node, and refreshes every fifteen seconds. The data is also at
/api/v1/fabrics/{id}/topology.
Placement reads the map: a replica spanning nodes takes nodes of one
leaf together when it can, and nodes whose cable trained short last.
Static assets are named by their content, as the stylesheet already
was.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
A fabric's identity was its master subnet manager, which changes on a
failover: for the minute its ports took to agree, one fabric read as
two, and a name covering it as two separate fabrics. Each agent now
also lists every subnet manager on a fabric (saquery SMIR, through one
port per master, once a minute); managers listed together are one
fabric, named by the lowest GUID among them, so the identity survives
the master changing.
The same list says what a fabric can survive. The cluster page's new
subnet manager table, /api/v1/fabrics, doctor and metrics
(llmgw_fabric_master_sm, llmgw_fabric_subnet_managers,
llmgw_fabric_problems) show each fabric's master, priority and
standbys, and say when a fabric has no standby, its ports disagree on
the master, ports are up with no subnet manager (INIT), or the master
changed in the last hour. Every change of master a port reports is
kept, and a fabric's last day of them is listed.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
A fabric was what agent.yaml called it. With several independent
InfiniBand fabrics at a site, two given one name would have had a
replica spread across both, starting and then hanging on its first
collective. Each active InfiniBand port now reports the master subnet
manager it sees (sminfo, asked once a minute), which every port on one
fabric shares and ports on separate fabrics cannot; a RoCE port reports
the IP network of its RoCE v2 address. Ports also carry their node and
port GUIDs.
Placement divides a declared fabric by that physical identity and forms
a replica on one part only; a node whose adapters for one name are on
two fabrics is refused, and a node that cannot say is kept apart from
those that can. /api/v1/fabrics and the cluster page list each physical
fabric with its subnet manager, and say when one name covers two
fabrics, two names one fabric, an adapter is up but undeclared, or a
node cannot be checked. doctor reports each port's subnet manager, and
an agent on a node with adapters installs infiniband-diags when sminfo
is missing.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
A port's state was read once, at registration: one that went down later
left its node on the fabric, offered multi-node work that would hang on
its first collective, until somebody restarted the agent. The agent now
re-reads every IB and RoCE port on each heartbeat - state, physical
state, rate and the error and data counters - and when the fabrics it
can carry traffic on change, says so once; the control plane replaces
the node's fabrics, which is what placement reads.
The ports are exported as llmgw_ib_port_active (with state and
phys_state, so an unplugged cable reads differently from a missing
subnet manager), llmgw_ib_port_rate_gbps and llmgw_ib_port_counter_total,
and a node's page lists them with the fabric each carries and any error
counter that is not zero.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
The release binary is built without cgo, so without NVML, and NVML was
the only source of NVLink peers: on every NVLink machine the portable
agent reported none, and tensor-parallel groups were chosen by GPU index.
Discovery now reads `nvidia-smi topo -m` after either path, for the
NVLink peers (kept from NVML where it gave them), each card's NUMA node,
and how far each network adapter is from it - PIX, PXB, PHB, NODE or
SYS - which travels to the control plane as nic_paths for placement to
use. Both the NICn-with-legend layout of newer drivers and the
adapter-named columns of older ones are read.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
The nodes are CPU machines, and nothing measured how busy one was: the
heartbeat carried GPU memory and disk, and llmgw_node_memory_bytes is the
total. The agent now reads /proc between heartbeats - CPU across all
cores, load averages, memory used and available, and each engine's
process group's cores and resident memory - and sends it with the
heartbeat. Nothing new runs on the nodes and Prometheus needs no new
target: the control plane exports it with the rest of the fleet, as
llmgw_node_cpu_utilization_percent, llmgw_node_cpus, llmgw_node_load,
llmgw_node_memory_used_bytes, llmgw_node_memory_available_bytes,
llmgw_shard_cpu_cores and llmgw_shard_memory_bytes. A measurement more
than a minute old is left out rather than repeated.
The cluster page's node table shows CPU and RAM as bars, and each node
links to a page of its own: current CPU, RAM, load and disk, the engines
on it with their cores and memory, and an hour of CPU, RAM, load,
per-model cores and memory and queue depth from Prometheus. It refreshes
in place.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Seeing what a node did meant ssh through a jump host, to a machine whose
address nobody remembers, to read a journal only root may open. When an
engine install failed on a new node today, the reason was one line — and it
was four steps away from the page that said the install had failed.
Each node's row on the cluster page now links to its logs: the agent's own,
and every engine running there, chosen from the list the node itself sends.
The page can follow, refreshing every five seconds, and is on both the admin
listener and /admin. `llmgw ctl logs NODE [--source SHARD] [-n N]` reads the
same.
They travel over the stream the agent already holds, so they need nothing
the control plane does not already have: a request goes down, the lines come
back, and a reply that does not come in ten seconds is an agent too old to
answer. The agent keeps its last 2000 lines in memory as well as writing them
wherever it did before; the engines' last few hundred lines were already kept
and sent only when one crashed.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
A node ran whatever llama-server somebody had once unpacked on it. Onboarding
checked an engine only when told its path, installed none, and a node with
nothing on it registered as ready. The one time that went wrong it went wrong
invisibly: the binary was there, executable, and could not start for want of
libgomp1, while the node reported healthy.
The control plane now says which engines every node has, at which version —
`engines:` in server.yaml, defaulting to the llama.cpp build this release was
checked against — and each agent converges on it. What only the node can
know, the node works out: the build for its processor and driver (CUDA with
its runtime when an NVIDIA driver is loaded, CPU otherwise), the OS packages
that build needs from its own package sources, and whether the result runs.
Every archive is checked against the sha256 GitHub publishes for it and
unpacked refusing any path or link that leaves the install directory. ldd
names a missing library outright; running `--version` proves the rest. Only
then is a directory marked installed, and it is checked again every ten
minutes, because an unrelated upgrade can remove a library.
An engine is reported only once installed and seen to run, or when the
agent's configuration names it on purpose — never because something happened
to be on PATH. The agent now says when it has probed, so an empty list means
"has none" rather than "too old to say": a node rebuilt from nothing is no
longer a candidate for every model at the moment it can run none of them.
Placement's refusal carries the node's own words, "installing: downloading
llama-b10991-bin-ubuntu-x64.tar.gz (16 MB)", and so do `ctl nodes` and the
cluster page, along with a warning for a CPU without AVX2 — the VM CPU type
that makes everything five times slower and nothing look wrong.
Agents also report their OS, architecture, vector extensions and NVIDIA
driver. Onboarding installs llmgw itself from the CI release for the node's
architecture, checked against the release's checksums, rather than copying
whatever binary the operator's machine had.
vLLM and SGLang are not installed yet: they are Python environments of
several gigabytes, not an archive, and still have to be named in the agent's
configuration.
Also fixes a race on the weights fingerprint, which two heartbeat loops touch
during a failover.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Every agent file on the cluster named its own node, its own address, the
path to llama-server and two weight directories — different on every node,
kept true by hand, and not true: node05 carried "ram: 32g" beside a measured
31 GB, looked for weights in an empty directory while fetching them into
another, and the other four never looked in theirs at all, so four nodes
reported no disk. Growing a node's RAM would have gone unnoticed, because
memory was read once, at registration.
The agent now finds these out. Its id is the hostname, which is also the
certificate's common name. Its address is the one on the route to the
control plane, which the kernel picks for a UDP dial without sending
anything. llama-server is looked for on PATH and then where release archives
are unpacked. A missing nvidia-smi is a node without NVIDIA cards rather
than a failed discovery — which also cut discovery short before InfiniBand
on every CPU node not told to skip GPUs. Fetched weights land in
/var/lib/llmgw-weights by default, and wherever they land is always looked
in.
Memory is read on every heartbeat, and installed engines are probed again
each minute and sent when they change, so a VM given more RAM or a node
given vLLM becomes a candidate without anyone restarting its agent. The
control plane logs both changes, since "the node now qualifies" is the
answer to why a model placed an hour after it was asked for.
What is written still wins. The agent file shrinks to the control plane's
addresses and the TLS files, the same on every node; onboarding writes only
the overrides it was given. What cannot be found stays configuration: which
fabric an adapter is on, because OpenSM's default prefix is the same on all
of them.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
The stale-profile flag could not fire where it matters. The control plane
keeps no record of a running replica across its own restart — it rebuilds
them from what the agents report — and adoption left the fingerprint empty,
so every replica read as unknown afterwards. That is precisely the moment
the catalog is most likely to have been edited: change the configuration,
restart the server, and nothing would ever say the fleet disagrees with it.
The fingerprint now travels with StartShard, the agent keeps it beside the
pool and fabric it already echoes back, and adoption takes the replica's
version from the agent rather than from the catalog it is about to be
compared against. An agent too old to report it sends nothing, which still
reads as unknown rather than as matching.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
The agent has always logged a percentage as it fetches weights, with a comment
saying a replica pulling a hundred gigabytes and one that is wedged look
identical from the control plane. They still did: the log is on the node, and
the node is not where anyone is looking when a replica has been starting for
ten minutes.
Progress now rides on the shard status and appears under the replica in `ctl
replicas` — a line rather than a column, because most replicas are not
downloading anything and a column would be empty for all of them.
It is deliberately not a state transition. Treating each chunk as one would
re-mark the shard as starting on every report and reset the timer that decides
when a slow start has become a failed one, so an hour-long download would keep
a doomed replica alive indefinitely. It arrives on its own method for that
reason, and a real transition clears it — otherwise a finished download sits in
the listing at ninety-nine percent under a shard that has been serving for an
hour.
Watchers are keyed by source rather than by shard, because a fetch is
single-flight: eight shards starting together produce one download and all
eight are waiting on it.
No percentage is invented when the server sent no length. One that stops moving
is worse than a byte count that keeps rising, so the field is absent and the
listing says "so far".
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Found by answering "where can we see this live". `ctl weights` was offering a
file for deletion that I had deleted two days earlier, and the node's disk
figure was the one it had when its agent started. Discover() is called at
registration and nowhere else, so both were frozen.
Disk is a fact about a moment, not about a machine. Sampled once, the figure
is wrong on exactly the node worth watching — the one busy filling up — and it
stays wrong until that agent restarts. The heartbeat already refreshes GPU
memory for the same reason, with a comment about noticing a foreign process
"after registration"; disk belonged beside it and I did not put it there.
The stale list cut both ways. A model fetched after registration was invisible
until a restart, so placement could not prefer the node that had just spent ten
minutes downloading it, and the disk check could not see the space it used.
Storage goes in every heartbeat, being a few numbers per filesystem. The file
list goes only when a fingerprint of paths and sizes changes, with a flag
saying the list is meant — without that, an empty list would be ambiguous
between "this node now holds nothing" and "nothing to report", and the second
reading would empty a node's inventory five seconds after it registered.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Two halves of the same problem: nothing stopped a model being placed on a node
that could not hold it, and nothing ever removed the weights of a model that
had been deleted from the catalog.
Placement now has a disk check, shaped exactly like the memory one it sits
beside, with one addition: it is skipped on a node that already holds the
weights. A node holding the file needs no room for it, and without that the
node best placed to run a model — because it already has it — is the one most
likely to be rejected, since holding the file is what used the space.
Reclaiming is the dangerous half, so the whole design is about what it will
not do. llmgw deletes only files it fetched itself, and that is a calculation
rather than a heuristic: the cache name is a hash of the source, so the set of
wanted files can be computed from the catalog exactly. Anything without that
name was put there by an operator — scp, a shared mount, a copy by hand — and
is none of this system's business however unreferenced it looks. A model that
took a week to copy must not be removable by a command someone ran to tidy up.
The node checks every path again before unlinking it, and that duplication is
the point. The control plane knows the catalog; the node knows its disk. A
control plane that is wrong, newer than the agent, or tampered with must not be
able to talk a node into deleting something, so the agent refuses anything
outside its own cache directory or without the cache name — including a path
that tries to traverse out of it.
Listing is the default and deleting takes --collect. The summary says "asked to
remove", because each node decides, and one that refuses a path it cannot prove
it fetched is this working rather than failing.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Disk was the one resource nothing reported. `statfs` was already being called
on every model directory, but only to ask whether the filesystem was a network
one — the free space it returns in the same struct was thrown away. So the
only way to find out why a node was filling up was to ssh to it, which is what
this system exists to avoid.
Reported per filesystem rather than per configured directory. Free space
belongs to the disk, not the path: two model directories on one disk are one
pool of bytes, and counting them separately would let the control plane add
24 GB to 24 GB and place a 40 GB model on a node that has 24.
Shared filesystems are summed separately from local ones and left out of a
node's own total. Space on a filer belongs to everyone mounting it, so twenty
nodes would otherwise each report the same free terabyte, and a scheduler
would place twenty models into room for one.
Nothing reported means nothing is known, everywhere: an agent too old to send
storage and a node with no model directories both send nothing, and both must
read as unknown rather than as a full disk. `ctl nodes` and the dashboard show
a dash, the metric is absent rather than zero, and a missing directory — which
is what an unmounted filer looks like — is skipped rather than reported as
having no space.
Shown as free out of total, because the first is useless without the second:
8 GB free is comfortable on a 10 TB filer and nearly full on a 10 GB root
partition, and only the second stops a model being placed.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
