Reference topologies built on Satchit Edge and Vishwakarma silicon — from a single factory-floor controller to a sovereign data centre. Every case runs the same hallucination-free Sudarshana framework, on your hardware or ours.
Mode 01 · your datacenterMode 02 · pay per inferenceHybrid
Case 01Mode 01 · Your datacenter
Industrial 5.0 factory floor
An E-7 class Satchit Edge controller sits on the factory floor, running deterministic vision inspection and line-control inference under 10 ms — no cloud round-trip in the critical path. Fleet-wide model updates sync from Sudarshana Cloud between shifts.
→Model updates ↕ Sudarshana Cloud (sync between shifts)
Case 02Mode 01 · Your datacenter
Sovereign data centre
A rack of S-9 accelerators trains and serves inside your own walls. Nothing leaves the building: telemetry to Sudarshana Cloud is read-only and optional, and the in-fab interconnect keeps multi-node training on one fabric.
Sovereign by construction · 3.2 PFLOPS per node
Topology
→S-9 × N — training + serving, in-fab interconnect
→Zero data egress · all models and data inside your walls
V-3 class handsets run always-on vision and language inference entirely on-device. Heavy batch workloads spill over to Sudarshana Cloud, billed per inference, and model updates flow back down to the fleet bidirectionally.
On-device first · cloud only for heavy batches
Topology
→V-3 handsets — always-on vision, on-device
→Batch workloads ↕ Sudarshana Cloud — pay per inference
→Bidirectional sync of model updates to the fleet
Case 04Mode 02 · Pay per inference
Retail wearable mesh
W-1 rings and badges run on-body sensor inference at sub-1W. An in-store E-7 gateway aggregates the mesh, and anything beyond local scope is handled by Sudarshana Cloud with per-inference billing — no hardware capex for the retailer.
Zero capex · billed per inference
Topology
→W-1 rings & badges — on-body inference, sub-1W
→In-store gateway (E-7) — aggregates the mesh
→Beyond local scope → Sudarshana Cloud, per inference
None of these match your shape? We co-design the deployment with you — tell us the workload and the walls it has to stay inside.