Caladrius

Caladrius for inference providers

Accountable for the customer experience, on infrastructure you don't own.

You run the models your customers depend on, on GPU clusters rented from neoclouds and hyperscalers, and you answer for the whole path. That path splits at a demarcation line between your serving layer and the rented infrastructure. Caladrius runs on your own nodes, on every cluster you rent. When latency starts to bite or requests fail, it names the cause in minutes, not hours, and shows which side of the line it sits on. Above the line, it drives the fix at the automation level you set and verifies it held. Below the line, it localizes the fault to a specific neocloud, with everything in your platform already ruled out: the evidence to escalate. It often identifies a degradation while it is still forming, before your customers feel it.

Rented infrastructure

Your customers

Your serving layer

Platform or neocloud?

Every inference incident lands on you first, and it opens with a question whose answer can sit where you cannot look: the serving platform, or the GPU infrastructure underneath it? By hand, the answer costs hours: an engineer correlating serving signals against GPU, fabric, storage, and host telemetry—TTFT against XID codes, queue depth against NCCL timings—on every neocloud, while requests time out and the customer waits.

Caladrius sees what your clusters see, on every neocloud at once, and correlates the full signal set to name which side of the line owns the problem. In your platform, that is a named root cause with the fix ready to run at the automation level you set—recommend only, on your approval, or automatic for the playbooks you have promoted. A serving regression after an engine bump, an autoscaler lagging a burst, a router landing off-prefix, a replica in a restart loop: named, fixed, verified. Below the line, it is the evidence that localizes the fault to a specific neocloud, with everything in your platform already ruled out. The neocloud starts from your evidence instead of from scratch: a faster fix on their side, and no finger-pointing on the way.

You straddle the line. Caladrius works in both directions.

Facing your neoclouds

Out of your reach, not out of view.

Your nodes cannot see a neocloud's switches, spine, or storage backend. What we give you, per neocloud, is the node-side evidence (the HCA's own link counters, NCCL timeouts, a GPU throttling, an ECC error climbing), everything in your platform already eliminated, and which neocloud the fault localizes to. That is an escalation the neocloud has to act on, not a ticket you have to argue. Where a neocloud is degraded and the fault is theirs to fix, Caladrius can route around it, so the deployment keeps serving while they do and the hours lost to blind debugging come back.

Facing your customers

Answer with authority.

When a customer asks why their inference was slow, the answer is a named cause, not a shrug: the cold-start storm, the KV-cache thrash, the degrading link, and what was done about it. Problems in your own layer get fixed at the automation level you set and verified, and the whole loop runs scoped per customer, so one tenant's burst is visible as exactly that.

If a neocloud you rent from runs Caladrius too

That neocloud's Fleet Console sees both sides of the line directly. Your evidence lands there already attributed, and the neocloud has likely already caught the fault and started the fix before your escalation arrives. Both sides read the same evidence, so the escalation is a handoff, not a negotiation.

One pane across every neocloud

Each neocloud can show you its own estate at best. Caladrius gives you the view none of them can offer: every customer deployment, mapped to the GPUs, fabric, storage, and neocloud running it, in one pane. Visibility is node-side and tenant-isolated, with every deployment scoped to its customer and access on grant: no rack access, no neocloud cooperation, and agents deployed in your own clusters in an afternoon.

What goes wrong—and who owns the fix

The platform layer

You fix it

The inference-serving layer you operate. Caladrius names the cause, drives the fix, and verifies it held.

  • TTFT p99 breachqueue time climbs while every node metric stays green
  • Streaming stall mid-responseTPOT degrades under KV pressure
  • Cold start on scale-uplong seconds to first token from zero
  • KV prefix miss or cache thrashthe router lands off-prefix
  • Engine version regressionthroughput drops after a vLLM or TensorRT bump
  • Queue depth explosionadmission sheds load and customers see 429s
  • Noisy tenant starves the poolone customer's burst, everyone's latency
  • Replica restart loopOOM at long context, then a cold start, repeatedly

Demarcation line

The neocloud

You escalate it

Node-side symptoms localize the fault to a specific neocloud; your platform is already ruled out.

  • NVLink or NVSwitch degradedintra-node collectives slow
  • Silent degradation, no XIDmeasurably slower, nothing logged
  • Thermal or power throttleclocks halve; the cause is inlet temperature or power on the neocloud's side
  • NCCL collective hangthe job wedges with no useful stack
  • PFC pause storm or congestiona saturated uplink you cannot see, showing up as link errors you can
  • Storage-fabric MTU or PFCcheckpoint and model loads slow to a crawl, silently
  • Unannounced maintenance or reclaimnodes drained on the neocloud's schedule
  • Spot preemptionseconds of warning, no reason given

What the agents see, and what they cannot

Where the agents run

Inside your clusters, on every neocloud in use: Kubernetes, and the same node-side footprint on each

What they collect

Inference-serving signals (TTFT, TPOT, tokens per second, KV-cache, queue depth, cold-start latency) alongside GPU telemetry (XID, ECC, thermal, clocks), the HCA's own InfiniBand or RoCE counters, RDMA and NCCL timings, PCIe, host metrics, and mounted file systems

What they cannot see

Each neocloud's switches and spine, its NVSwitch fabric, its storage backend, the far side of any link

What proof means here

Node-side evidence plus everything in your platform ruled out, and which neocloud the fault localizes to. Never a measurement of a neocloud's gear.

Where the fix runs

In your serving layer, at the automation level you set. Below the node, an escalation to the right neocloud with the evidence attached.

Act on what you own, at the automation level you set

Every remediation in your own layer runs the way you decide: recommend only, execute on your approval, or execute automatically for the playbooks you have promoted, within the permissions you grant. Serving config, autoscaler settings, routing, a replica restart: start with recommendations, watch what Caladrius would have done, and promote one playbook at a time.

Whichever level runs it, the fix is not done until it is verified. Caladrius checks that latency came back and errors cleared against the deployment's own indicators, and rolls back if they did not, so a wrong fix costs seconds of one deployment rather than a customer.

Pass the visibility down

Every deployment is scoped to its customer, and its reliability picture can be passed to the customer as part of what they buy from you: what happened, where it sat on the line, what was done, and whether it held. The same Workload Console that answers your platform team's questions gives each customer a per-deployment view of theirs. Reliability becomes something you show, not something you promise.

SLA breaches customers see

often caught before customers feel them

cost per million tokens

GPUs serving, not stalled behind faults

  • Fewer SLA breaches customers see

    Degradations often caught while still forming, before they reach your customers' users.

  • Less time lost to 'platform or neocloud?'

    A named cause in your platform or a fault localized to a specific neocloud, in minutes, not hours, with the evidence to act on it, so incidents resolve or escalate fast instead of consuming engineering days.

  • Hold neoclouds accountable

    Escalate the right neocloud with node-side evidence and enforce the SLA you pay for; faults you would otherwise absorb become their problem to fix.

  • A trust advantage

    Pass per-deployment reliability visibility to your customers as part of what makes your platform worth choosing.

  • Lower cost per million tokens

    GPUs serving requests instead of stalling behind unresolved faults, across every neocloud.

Fewer breaches, cheaper inference, and reliability you can both defend and sell.

Often, the customer never notices

Caladrius often identifies the cold-start storm building, the KV-cache filling, or the link degrading while the problem is still forming, with the action to take. The deployment keeps serving and the question never gets asked.

Latency biting or requests failing right now?