COMPUTE ATLAS Supercomputer supply-chain graph
1581 systems 558 sites Sourced data

Supercomputers/Systems/Vyoma Chennai B300 AI Factory (Together AI)

India · planned · mixed

Vyoma Chennai B300 AI Factory (Together AI)

Also known as L&T Vyoma B300 AI Factory; LTN Compute Chennai

Operated by Vyoma.AI at Vyoma Chennai Campus .

Researched with AI assistance, checked by scripts. These rows were researched by AI agents reading public operator, laboratory and vendor sources, appended by scripts and checked by automated validation; no subject-matter expert has reviewed them (how this site is made). A mechanical second-reader pass has since fetched every cited source: 1350 of 1581 systems have a readable citation that names them, and 64 are genuinely weakly sourced. Every claim carries its source and a confidence tier. Treat anything below verified as a lead, not a citation.

Measured performance

Rmax
-
Rpeak
-
Rmax ÷ Rpeak
-
Cores
-
Power
-
Per watt
- GF/W

Figures are as last publicly reported for the configuration described below, not a live measurement. Where a system was upgraded in place, the post-upgrade configuration is shown and the earlier one appears in the timeline.

What this machine is made of

One row per supplier relationship. “Supplier at build” is the company that shipped the part at the time; where that company has since been acquired, the parent it rolls up to today is shown beside it. That distinction is what makes ticker-level aggregation possible across a thirty-year dataset.

Role Part Supplier at build Quantity Confidence Source
Integrator -
Vyoma.AI via LTN Compute delivers the data centre, compute, networking, storage and operations
Vyoma.AI
rolls up to Larsen & Toubro
- Reported larsentoubro.com
Accelerator NVIDIA B300 SXM
Accelerators
CUDA (Blackwell Ultra) · TSMC 4NP · 1,100 W
10,000 NVIDIA B300 GPUs in a single cluster
NVIDIA 10,000
reported
Reported larsentoubro.comcrnasia.com

AI datacenter metrics

Figures beyond an accelerator count, each with who stated it. What can and cannot be compared across AI datacenters.

MetricValueAs ofBasisNoteSource
Accelerators 10,000 accelerators 2026-08-13 Design target L&T states 10,000 NVIDIA B300 GPUs in a single cluster for Together AI; no go-live date given. larsentoubro.comcrnasia.com

The read

Larsen & Toubro's 13 August 2026 press release says Vyoma.AI, through its subsidiary LTN Compute, secured an order to deploy 10,000 NVIDIA B300 GPUs in a single cluster at Vyoma's Chennai data centre campus for the US AI cloud company Together AI, covering the data centre, accelerated computing, high-performance networking, parallel storage and operations for Together AI's training, fine-tuning and inference platform. L&T calls it India's largest single-cluster AI infrastructure. The same release says the campus is a gigawatt-scale site with a 250 MW first phase and 150 MVA of power readiness; those are campus figures, not this cluster's draw. The release gives no go-live date, no interconnect or storage vendor, and no order value in figures, so status is planned rather than under_construction. CRN Asia repeats the release, so the two sources are not independent. Together AI's earlier cluster is together-hypertec-gb200. E2E Networks' 1,024-GPU B200 cluster at a Chennai data centre is a separate row (e2e-chennai-b200); the fetched pages do not say whether it shares this campus.

Timeline

Site & facility

Change history

Nearby in scale

The machines closest to Vyoma Chennai B300 AI Factory (Together AI) by accelerator count, smaller to larger.

Same accelerator

Further reading