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>
ctl guard judge check, and POST /api/v1/guard/judges/check, time three
judgments of a 280-token prompt, then a burst at once, against the
policies' wait: ok, tight or slow, about how many requests a second can
be judged, and what to do. server init runs it once the judge is up and
says a machine too slow before the next steps; the wait is not changed
without asking. BACKLOG reordered by what goes wrong where installed.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Its tools say what llmgw ctl does: cluster_status, list_nodes,
list_models, list_replicas, explain_placement, node_logs; none changes
anything. The admin API serves it at POST /api/v1/mcp, and the gateway
answers a server registered as llmgw:admin in its own process, so no
token is kept and each control plane serves it. ctl mcp add takes
--bearer-file for a token sent as Authorization: Bearer.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
llmgw ctl mcp add|list|remove|test and /api/v1/mcp/servers keep the
servers; a token given with --secret-file is kept in the store, sealed,
and named by reference. keys limits --tools, and the console's limits
form, grant tools as patterns. Documented in install.md and clients.md.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
The startup timeout runs from when a node's download last moved, so a
model of hundreds of gigabytes on a slow mirror is not failed while it
arrives. ctl model serve --env sets engine variables (NCCL_DEBUG=INFO)
on every node, and a layout given by hand keeps expert parallelism for a
model of experts. docs/large-models.md: how a model is split, what each
way needs of a card, and a checklist for bringing one up on a fabric.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
A mixture-of-experts model on more than one card is served with vLLM's
--enable-expert-parallel; config.json's experts are read by any of their
names, and a model that also reads pictures is sized by its text_config.
Tensor parallelism past the KV heads is allowed when it is a multiple of
them (Qwen3-235B, four KV heads, runs on eight cards), which the plan
had refused. Several nodes are offered in any number, not only powers of
two. Each way says what it needs of a card, part by part, and of all its
cards; the serve form checks a context longer than planned still fits.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Found on a fresh HA install with a judge machine: the leader saw the
policy's judge missing while init was still fetching it, served one
itself, and its entry replaced init's, so a second judge ran off the
judge machine. The keeper now waits ten minutes after it starts, and a
serve job it starts gives way to a model added meanwhile (AddNew).
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
The judges' machine was selected by the judge's profile, but any other
model could still be placed beside it. A node labelled llmgw.role now
takes only profiles whose selector asks for that role.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
A judge a policy names and the catalog lacked was served with 3 GB, no
cores and llama.cpp's prompt cache; on a busy node its judgments missed
their budget and fail: closed refused the requests. It now gets init's
2 GB and cores, and every judge modelserve serves runs with
--cache-ram 0.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
People → Sign-in shows single sign-on, Active Directory and SCIM, and
the directory's last sync. E sets up Entra ID from the tenant and client
IDs; D sets up Active Directory, tried from the control plane first:
each server bound, people who may sign in, members of each mapped group.
The secrets go into the store as store:auth/..., sealed by the master
key, and the CA into the settings, so no control plane needs a file.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
An external model takes api_key_files, each a file and an optional weight,
in place of api_key_file. Each key is an endpoint of its own
(external:MODEL#1, #2), so the router's scoring, retries and breakers work
per key. A key answering 429 is passed over while its breaker is open. A
key answering 401 is passed over too, and external_key_refused is sent,
naming the endpoint and never the key; with a single key the 401 is still
the client's. A key whose file cannot be read is left out, and usage
records which key answered by its endpoint.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
CI run 394, on a commit that changed only BACKLOG.md, failed with a data
race in TestAVisionModelIsServedWithItsProjectorBesideIt. The serve job's
goroutine wrote j.Request without the lock (since efffdb6, which sized
embedding slots), while Get's snapshot read the job under it. Every other
write to a running job holds the lock. It did not reproduce in 30 runs
here; the race detector's trace names this write and that read.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
A v0.14.6 install on fewer than eight cores refused every request until
its judge was given cores by hand, and upgrading did not change that. The
judge keeper, on the leader, now finds a judge whose entry is exactly what
init before v0.14.7 wrote: one llama.cpp CPU profile, an 8192 context and
nothing else, 2 or 4 GB, none to two cores. It gives the judge 2 GB,
--cache-ram 0 and cores by init's rule through modelsvc.SetProfiles, then
restarts its ready replicas. The replica count is left as it is. A judge
whose entry differs is left alone, and the log says so once.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
