Skip to content
Back to Edge & GPU Computing

Specification sheet · Cloud & Hosting

Dollu Ltd

dollu.com

[email protected]

+91 777-500-2222

Edge & GPU Computing

Edge compute at Dollu PoPs and GPU instances for training and inference - so latency-critical applications and private AI for voice, contact-centre and analytics workloads run on your carrier's network, not across the internet.

Edge compute nodes at Dollu PoPs and GPU instances for AI training and inference, with private AI stacks for voice, contact-centre and analytics workloads.

PoPs eligible for edge nodes
40+
Edge round-trip in metro
< 10 ms
GPU classes available
H100 / L40S

At a glance

  • Edge nodes at Dollu PoPs, colocation or on your premises
  • Metro round-trip under 10 ms; private paths to central regions
  • Local breakout for private 5G, SD-WAN and IoT traffic
  • L40S and H100 GPUs, on demand, reserved or bare metal
  • Pre-built CUDA, PyTorch, Triton and vLLM images; NVMe scratch
  • Managed Kubernetes with GPU scheduling and autoscaling
  • Private AI for speech, agent assist, summarisation and fraud
  • Data stays in-region; bring your own models or use open weights

Typical use cases

  • 01Contact centres and CCaaS
  • 02Conversational AI and voicebots
  • 03Video analytics and smart sites
  • 04Manufacturing and private 5G
  • 05Gaming and interactive media
  • 06Fraud and network analytics

Technical & commercial specifications

Edge locations40+ Dollu PoPs, partner colocation, on-premises appliances
Edge latency< 10 ms metro round-trip; private backhaul to regions
Edge form factors1U single node to multi-rack; Kubernetes or VM hosts
GPU classesNVIDIA L40S; H100 SXM with NVLink; fractional GPU for dev
GPU regionsMumbai, Frankfurt, London, Ashburn, Singapore
InterconnectUp to 400G between training nodes; NVMe scratch; parallel FS
SoftwareCUDA, PyTorch, TensorFlow, Triton, vLLM; managed Kubernetes
ConsumptionOn demand hourly, reserved 1–3 years, dedicated bare metal
Data controlsIn-region only; customer-managed keys; no third-party telemetry
Support24×7 NOC; P1 response ≤ 15 min; named account manager

Talk to Dollu about Edge & GPU

Send us your destinations, volumes, sites or use case and we will return a proposal, pricing and a technical plan within one business day. Test credentials and the full service description and SLA document are available on request.

NOC
[email protected] · 24×7

Dollu Ltd · 2403A, Iconic Corenthum, Sector 62, Noida 201301, India. This sheet summarises the standard service; specifications may vary by country and are confirmed in the service order.

Online version: https://dollu.com/services/cloud/edge-gpu-computing