Specification sheet · Cloud & Hosting
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 locations | 40+ Dollu PoPs, partner colocation, on-premises appliances |
|---|---|
| Edge latency | < 10 ms metro round-trip; private backhaul to regions |
| Edge form factors | 1U single node to multi-rack; Kubernetes or VM hosts |
| GPU classes | NVIDIA L40S; H100 SXM with NVLink; fractional GPU for dev |
| GPU regions | Mumbai, Frankfurt, London, Ashburn, Singapore |
| Interconnect | Up to 400G between training nodes; NVMe scratch; parallel FS |
| Software | CUDA, PyTorch, TensorFlow, Triton, vLLM; managed Kubernetes |
| Consumption | On demand hourly, reserved 1–3 years, dedicated bare metal |
| Data controls | In-region only; customer-managed keys; no third-party telemetry |
| Support | 24×7 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.
- Sales
- [email protected]
- Phone
- +91 777-500-2222
- Web
- dollu.com
- 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
Contact: https://dollu.com/contact?service=edge-gpu-computing