With slurm.users llmgw, each project is a Slurm account, its organization's
and team's above it, with the project's members and its team's and
organization's on it; slurm.conf holds a job to its user's accounts. The
controller's agent keeps them with sacctmgr, only what it made, and reports
the jobs that ended in the last day; the leader records each once, its
GPU-hours (core-hours without cards) priced at auth.gpu_hour_cost into its
project's usage as model slurm/PARTITION.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
auth.gpu_hour_cost (and core_hour_cost) is what an hour of a GPU (a core)
costs the operator. The leader keeps, by the hour, the GPU- and core-hours
each model's replicas hold (held_1h); llmgw ctl prices suggest spreads a
model's over the tokens it served, an output token counted as four input
ones and a cached prompt token as a tenth of one, and --apply writes the
prices into auth.pricing. Idle hours are in the cost, so a model held and
little used comes out dear; one held and billed nothing is shown with what
it held.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
slurm.containers (ctl slurm containers on) has every Slurm machine's agent
install enroot from NVIDIA's release and build pyxis against its own
Slurm, both pinned and checked against their digests, and on GPU machines
nvidia-container-cli from NVIDIA's repository. enroot keeps each user's
containers under /run/enroot and /var/lib/enroot, needing no login
session, with the shared path in every container. The leader has Slurm
load pyxis only once every machine reports it: plugstack.conf's
"required" fails every job on a machine without the plugin.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Tried on the PoC: lending cuda01, the one GPU node, its model had nowhere
else to go and waited out the drain's five-minute grace, while ctl slurm
status said only "1 replica(s) still to move off". It now says the time
that replica is stopped at. Also recorded: Slurm on a GPU node, tried on
cuda01 (gres, ConstrainDevices, accounting of gres/gpu).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Setup asks for webhooks, but one left empty was never mentioned again: a
lost node or a judge down was told nobody. With no notify.webhooks in the
cluster's settings, ctl status and the console's Overview say so, and how
to set one. BACKLOG: the judge's refusal after a placement change, tried
again on idle VMs, did not happen; a cold judge's first answer is 2-3x
slower but inside its budget.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
slurm.shared mounts the site's NFS export, has an llmgw node export the path
over NFS to the Slurm machines alone (2049 in the firewall), or looks for a
file system the site mounts. slurm.users "llmgw" makes each active account a
Linux user on every Slurm machine: login from its e-mail, a UID from 200000
kept in slurm_users and never reused, its home on the shared path, its SSH
keys from the portal's Profile (or ctl slurm users keys) read by sshd from
/etc/llmgw/ssh-keys. server init --slurm chooses /shared from the first
machine and llmgw's users; --slurm-shared and --slurm-users change that.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Since 23.11 Slurm runs badly without accounting storage: the main
scheduler passes every job by as InvalidAccount. slurmdbd takes MySQL or
MariaDB only, so the controller's agent installs MariaDB beside it,
answering that machine alone, makes the database and its user (the
password made from the munge key, never on a command line), runs
slurmdbd and adds the cluster, all before slurmctld. A MariaDB that was
on the machine before keeps its settings. slurm.conf accounts the jobs
there, with what each used from its cgroup and the cards, and the
priority is multifactor again. Port 6819 joins Slurm's in the firewall.
ctl slurm status and the console say whether slurmdbd runs; the install
screen, server init --slurm and the guide say what is put where.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Without accounting storage, 23.11's default priority/multifactor has the
main scheduler pass every job by as InvalidAccount; backfill started it a
pass later. slurm.conf sets priority/basic.
Every node was written State=DRAIN, so each start of slurmctld on new
files drained a lent node again until its agent resumed it. A lent node
is written without it.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
On a cluster upgraded to the kept nodes, the first leader finds none and
wrote slurm.conf without the nodes it had not heard from yet, as before.
A node neither reported nor kept now holds the controller's files back
for slurmsvc.HoldFor (2 minutes) from the leader's first pass.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Tried on the PoC: with a job on a lent node, the leader restarted and its
first slurm.conf had no node in it (none had reported to it yet), so
slurmctld dropped the node and the job ended in NODE_FAIL.
The leader keeps slurm.conf's nodes and the controller's address in the
store's cluster state (slurm-nodes); the next one starts from them and
writes the same files until the nodes report again. With the store
unread, the controller gets no files that leave a node out. A node is
told nothing, rather than that it has no part, until its controller's
address is known: no part stops slurmd, and its jobs with it.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The choices screen has a Slurm part, and --slurm writes slurmctld on this
machine's node and slurmd on every node, those that join later too, into
server.yaml. slurm.all_nodes (ctl slurm setup --all-nodes) takes the nodes
from the leader's inventory. No node is lent at install.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
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>
The same inputs place a replica on the same node and card, so an on-demand
model that failed to load there was started there again after every
backoff until it was parked. The reconciler remembers where a model's
replicas failed and places the next away from them when anything else
fits (Scheduler.Away); with nowhere else, there again.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The mirror page's form began every GGUF model at 4096 tokens, the
console's at 4096 or the plan's figure. Both now start at what the model
was trained for, cut to the most whose KV cache fits beside the weights
where the form places it; the mirror page's slots are as many of that, up
to four, as the room left holds. Plan carries the trained context.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
C1. A membership of an organization may be admin as well as member and
manager. An admin sees /org as a manager does and changes the
organization from it: its teams and projects, who of the approved
accounts is in them, its members' roles, and the keys spent in its
projects. Every id a form names is checked against the organization;
limits, accounts, the organization's name and the cluster stay with the
cluster's staff, and an admin cannot take their own role away.
A group from OIDC, SCIM or a directory no longer rewrites a membership
it names as a plain member at every sign-in, which took a manager's role
away (EnsureMembership).
Pages draw a form only for someone who may send it: Nav.May asks the
staff rule staffMay keeps, and a page whose forms a person may not send
gets no form token. A viewer sees the people, limits and mirror pages
without forms; an operator the mirror's.
Forms are compact: labels close to their fields, fields as wide as what
goes in them, smaller buttons, and the short forms on one line.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A sweep counted every file the nodes were asked to delete as freed as soon
as it asked, and a node refused a set's directory as not empty, so tens of
gigabytes were reported freed and nothing was. The agent removes a set's
directory whole (a link only as a link), and the control plane waits for
each node to list its files again, saying what it no longer lists and what
it kept.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The row of a served model leads to its card, which now changes its context
and longest answer, its cards, its replicas on each profile with a profile
on CPUs to add and its speed beside, stops, starts and restarts it, and
removes it with its files or without. Stopped on the row stops the model
rather than setting its scaling to nothing. The console gains Replicas per
profile, and ctl models shows the counts.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A profile's replicas, set on any of a model's profiles, is how many of its
replicas run there; the scaling becomes the sum. The reconciler starts the
ones short of their profile before stopping the ones over, so a change of
split never runs fewer. ctl model replicas sets them, adding a profile on
CPUs to a GGUF model; the router already fills the higher-priority pool
first, which the CPU profile is put below.
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>
Each router's per-counter request and token counts, this minute's and the
last, ride the standby's two-second exchange with the leader. The leader
answers each standby with everyone else's sum, its own included, and puts
the standbys' sum in force on its own router; each limiter adds the
others' counts to its sliding window.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
A standby follows the leader's Ready replicas over the agent port, every
two seconds, and reports back the replicas its router used and the
on-demand models it was asked for. No engine keys travel: every control
plane derives them from the cluster secret. Budgets are raised to the
store's every 30 s. Unheard from the leader for a minute, a standby
passes /v1 on as before. Off by default.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
max_output on POST /api/v1/models/{name}/context, --max-output on ctl model
context, and a field in the console's Context length… form. Alone it changes
only the catalog's limit, which the router holds max_tokens to, and starts no
replica again; with a context it is set with it, never past it.
Strata's context is now changed like the others', through its setup's
--context, which writes the engine's start script at each start. Neither
needs a model removed and added again any more.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
FreeToken (FlashML-org/FreeToken) serves mixture-of-experts models several
times a card's size from one card, experts in RAM, from Hugging Face
safetensors checkpoints. Installed like vLLM, from PyPI by uv, on every node
it runs on: compute capability 8.0+, driver 580+, x86-64, and the CUDA 13
toolkit it compiles kernels with. Older cards are passed over: on cuda01's
Quadro RTX 6000 (7.5) 0.2.1 had no kernel image for the first prefill, and
in fp16 hit an illegal memory access on its first request.
ft serve gets the model, address, card and served name; the key goes in
FREETOKEN_API_KEY. Flags that read files or fetch are refused, as are
FREETOKEN_ variables naming paths or the agent's own settings. ctl model
context sets --max-seq-len-override.
Readiness now also waits for an engine whose /health answers 200 while its
body says "loading", as FreeToken's does from the moment its HTTP server is up.
FreeToken is followed release by release: a weekly workflow fails when PyPI
has a version newer than DefaultEngines installs (scripts/engine_releases.py).
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>
llmgw ctl model gpus MODEL N [--profile P] [--in-place],
POST /api/v1/models/{name}/gpus and the console's GPUs…: how many cards of
one node each replica uses. Tensor parallel for vLLM, SGLang and
TensorRT-LLM, held to the model's KV heads (modelplan.SplitsHeads, now one
rule for the planner and this); the layers split for llama.cpp, its old
--tensor-split dropped. Refused for a count no node has, for cards that
would not hold the weights and the context, and for engines on one card.
The replicas start again beside the old ones; with no room beside them the
command says so, and --in-place stops each first.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
ctl model context MODEL TOKENS [--slots N], POST /api/v1/models/{name}/context
and the console's Context length…: the catalog, the engine's arguments and
the KV memory change together, refused past the trained context or what the
cards hold, then the replicas restart one by one.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Strata (github.com/Niko1221/Strata) keeps a mixture-of-experts model's
experts in RAM and the ones used most in VRAM; on cuda01's RTX 6000 it
serves Qwen3.8-Flash-Next 125B at 70-87 tokens a second to one client.
- engines/strata.go: the adapter. The agent starts llmgw strata-serve,
which runs Strata's setup the way its desktop app does
(STRATA_CONTROL_INSTALL: installs nothing, writes only under the
replica's and the node's directories) on the fetched GGUF files, points
the configuration it writes at the installed engine, and execs Strata's
server. The key goes in STRATA_API_KEY, never on a command line.
- A profile's args go to setup: --family, --size (setup's --model, which
is the source everywhere else), --context, --parallel, ... Flags that
move files or pick the engine or GPU are refused.
- provision: the source pinned by digest in a Python environment, and the
release's prebuilt engine unpacked beside it, checked against the digest
GitHub publishes: CUDA 13 (7.5+, driver 580) or CUDA 12.9 (6.0-8.9,
driver 575). Python builds can now carry release assets.
- Metrics are vLLM's names under /metrics/prometheus.
- The catalog wants one card and a family, and a directory, not one .gguf.
Opt-in: not in DefaultEngines.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
mirror.peers names the mirrors kept in step with mirror.api. The
mirror's management calls go to the first that can be reached, and
each mirror is asked every fifteen seconds whether it answers: a shard
is sent its model's and adapters' address on one that does while the
mirror the catalog names is down.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
- Revoking a server's tools takes them from every level beneath too, and a
level left naming no tool stays closed ([]) while any level above or
beneath names tools: an organization's revoke left its teams the copies
their first grants took, and going back to no list opened the level to
what was above it. A closed level is shown on the page and in the
console with an action to open it (store.OpenTools). A key's owner's
list is among the levels above a key.
- The flag check matches short flags as written again (-m, -hf, -mu were
let through), takes a long flag's beginning for it only for the engines
that parse with argparse (vLLM, SGLang, ComfyUI: --li is --listen), so
llama.cpp's own --chat-template is not refused, and refuses llama.cpp's
short spellings (-hfr, -hff, -mm, -jf, …).
- A stored model with an adapter by Hugging Face id can be changed again:
what it already had is not asked about anew.
- The catalog reads a Hugging Face id as the agent does (engines.IsHubID).
- The page's form cannot move llmgw:admin to another address.
- server init skips the memory check only where the gateway already runs,
not wherever a half-finished first run left server.yaml.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
From review. An adapter given by its id is downloaded by vLLM itself, and
a TensorRT-LLM model by its id by TensorRT-LLM, past the node's check and
not held to safetensors: a model with either is refused when it is added,
unless it says allow_pickle, with how to mirror its safetensors instead.
vLLM's own model by id stays allowed: the agent gives it --load-format
safetensors. A test holds every preset to its own pickle check.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
From review. A server's description, timeout and rate can be emptied from
the console and the page (MCPServerRequest.Clear), where an empty field
used to leave them as they were. An address with a user and password in
it is refused (adminapi.CheckMCPAddress): the credential belongs in a
header, sealed, and the address is shown and audited as written. The
console accepts llmgw:admin and the page lets it be changed, address
fixed. A grant to a key that is not there is refused rather than said
done.
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>
From review. A mirror set already on the node is looked at again, not
trusted for having been fetched once; Pickled cuts a query or a fragment
from any source, hf: too; .pt2 is a pickle. The flag check reads a flag as
the engine does: underscores as dashes and any beginning of a refused flag
as that flag, since argparse takes --trust-remote for --trust-remote-code;
SGLang refuses --load-format, which would undo the agent's safetensors.
TripoSR's preset says allow_pickle: without it the preset could not be
added and the presets pass failed on it each time. A shared ComfyUI
environment's hidden entry takes its first member's allow_pickle, as it
takes its source.
The GenAI trace attributes made temperature and top_p typed fields of the
request's parse, so "0.7" as a string was a 400; they are read loosely,
as they are read only for the trace.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
/admin/mcp, for administrators only, since a server's credential reaches
whatever it guards: each server's state, who has been granted its tools,
its rate, the headers it is sent by name with the sealed ones marked, and
its address; adding one with a bearer token or another header kept in the
store; testing it with its credential and listing its tools; granting them
to a team, project, org, person or key, written into that level's limits
beside its other grants and its rate and budget; revoking; changing;
replacing the credential; turning off and on; removing; and how a person
points an agent at the gateway's /mcp with a key of their own. English and
Turkish. The secret's field is named so the audit line redacts it.
The admin API's server merge and test are package functions now,
adminapi.MCPServerFrom and adminapi.TestMCPServer, shared by both.
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>
Judged by the nodes as they are now, through modelplan.Options, the
planner that serving a model uses: GGUF at Q4_K_M from the parameter count,
safetensors at the size the registry's dtype breakdown gives (packed AWQ,
GPTQ and MXFP4 at four bits), FP8 only where a card has compute capability
8.9, MLX safetensors never. A picture model is judged against one card. A
cluster with cards asks the registry for safetensors too, a hundred at a
time; one without asks for GGUF only. The page says what it judged by: the
largest card, its capability, the most RAM on one node.
On a repository's page a file set no node holds is marked with what it
needs, against what the best node offers, and has no Fetch button.
Tried against the PoC's seven nodes and Hugging Face's trending hundred:
63 shown, the rest too big for one 24 GB Turing card or FP8.
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 tool's answer is read by the caller's policies as the prompt it
becomes, so an instruction planted in a ticket is withheld and personal
data redacted; its arguments are read before they leave. ctl mcp add
--rate bounds each caller's calls a minute to a server (migration 0050),
and five failures in a row take a server out for a minute, its tools
off the list.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
The same text again was answered from what the engine kept of the last
reading, in a tenth of the time: the check read 4.9 s, then 0.5 and 0.5.
Each judgment now begins with a line of its own.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
