> solutions / zk

Managed operations for ZK prover farms and rollups

Proof generation is GPU-bound, deadline-bound and parallel all at once. One dropped job and you miss the block, and the reward with it. We build the farm, the queue, the retries and per-circuit benchmarks on SP1, RISC Zero, Boundless, Brevis.

Our stack is already built: SP1 and RISC Zero as the RISC-V zkVM baseline, Boundless and Brevis as decentralized prover marketplaces, Jolt and Halo2 for custom circuits. On your farm we set up a GPU scheduler with deadline-aware prioritization, kv-cache for circuit segments, retry queues with exponential backoff, and alerts for a missed proof window.

Our niche is the operator for operators on prover marketplaces. Succinct, Boundless and Brevis launched as marketplaces in late 2025, but no one yet will run your GPU farm on them under a signed SLA. We will.

[ Get a 48h deployment plan ]

stack we operate

This is the ZK subset, and the platform layer is identical across ICPs.

ZK: SP1 RISC Zero Boundless Brevis Jolt Halo2

Platform: Kubernetes Terraform Ansible Prometheus Grafana Loki OpenTelemetry PagerDuty

what we deploy

Concrete deliverables for ZK teams, and each one ships end-to-end with a repo, IaC and runbooks.

[ Prover farm with GPU scheduler ] →

H100 / A100 / 4090 pool, deadline-aware job prioritization, NUMA-aware placement, 75%+ per-card utilization in typical setups.

[ Proof-job retry queue ] →

Idempotent submit and exponential backoff, a dead-letter queue with per-circuit analysis, and an alert on a pre-deadline ETA miss.

[ Per-circuit benchmark catalogue ] →

Measurements on SP1 / RISC Zero / Jolt per circuit: time-to-prove, peak memory, optimal GPU type. Artifact cache for precompiles.

[ Operator on Boundless / Brevis / Succinct ] →

Marketplace registration, bidding strategy per circuit type, reputation tracking, payout reconciliation, marketplace switching by marginal cost.

[ ZK rollup ops: prover + sequencer + DA ] →

Proving stack for your own rollup: coordination across sequencer, batcher and provers, L1 finality monitoring, stall playbook.

what we operate 24/7

After handoff the pager lives with us, and we tune the coverage for ZK farms:

Prover liveness against network deadlines: alert if proof ETA exceeds 70% of the proof window.
GPU health watchdog: ECC errors, thermal throttling or xid signals trigger a preempt and job migration.
Queue depth / lag metrics per circuit: alert on >20% drift off baseline.
Auto-retry on failed proof generation with deterministic seed for reproducibility.
Versioned runbooks: prover crash, OOM on witness generation, stuck marketplace bid, L1 fork-choice inside the proof window.
Monthly perf review, where we look at new precompiles, refresh benchmarks and rebalance load across marketplaces.

migration scenarios

Here's what we move without losing payouts or skipping proofs.

single marketplace to mix

Move from a single prover marketplace to a portfolio of 2-3: differentiate by circuit type, hedge against single-venue downtime.

cloud GPU to bare-metal

Farm moved off AWS / GCP onto dedicated GPU at Latitude.sh / DataPacket: typical 50% cost-per-proof reduction, no deadline misses.

SP1 to RISC Zero (or back)

Parallel shadow proving for correctness, gradual cutover by circuit type, latency baseline pinned along the way.

scale-up for incentive season

Prover capacity 5x in 7-10 days: H100 burst selection, auto-onboarding into marketplaces, post-season wind-down playbook.

FP32 to FP16 / mixed precision

Quantization-aware proof generation where the circuit allows: 30% reduction in time-to-prove, re-verify check per batch.

onto in-house proving stack

From an external prover service onto your own farm: breakeven calc, gradual cutover, audit of key material and precompiles.

cases

All anonymized: NDAs cover the names, but the numbers are real.

ZK rollup · 6 mo · validator ops + prover farm · slashing: 0 · missed proof windows: 0

SP1 marketplace operator · 4 mo · 32 H100 · top-3 by win-rate · cost-per-proof -45%

RISC Zero proving service · 8 mo · 16 H100 + 24 4090 · ETA accuracy ±8%

Brevis incentive season · 8 weeks · 5x burst capacity · 99.4% on-time delivery

SLA tiers

Three coverage levels. For production proving with a signed deadline SLA we usually recommend Silver or higher.

Tier	Response p95 (Sev-1)	Coverage	Incident report	Engineer hours / mo
Bronze	30 min	Business hours, 5×8	Within 48h	40
Silver	15 min	24/7 on-call rotation	Within 24h	80
Gold	5 min	24/7 with dedicated engineer	Within 12h	160+

FAQ

Do you work with one zkVM or across all of them?

Across all of them: SP1 and RISC Zero for the RISC-V zkVM approach, Jolt and Halo2 for custom circuits, and Boundless / Brevis / Succinct as the marketplace layer. If you have a collab with a specific provider, we plug into their toolchain.

What happens if a deadline is missed?

That's a Sev-1: escalation in 5-15 min (by tier), root cause in 12-24h, then a postmortem with concrete action items. Architecturally we try to catch misses early, since an alert on ETA >70% of the proof window triggers a pre-emptive migration to a free GPU.

How many GPUs does a starter prover farm need?

It depends on the circuit and target throughput. For one production circuit the baseline is 4-8 H100 or 16-24 RTX 4090, and for a marketplace bid we start with 8-16 H100 and scale by win-rate. Send the circuit type and target proofs/hour, and we'll send a sized estimate in 24h.

Can you participate in a decentralized prover marketplace on our behalf?

Yes, it's one of our whitespace bets. We register as your operator on Boundless / Brevis / Succinct, run the bidding strategy, watch reputation and reconcile payouts, while staking material and payout wallets stay with you.

Do you support an in-house proving stack for a rollup?

Yes, and that includes sequencer + batcher + prover as a coordinated pipeline, L1 finality observability and a stall playbook. We can build the stack from scratch or take an existing setup into operations.