LOTA throughput per GPU
Company: CoreWeave
The claim, verbatim
CoreWeave's Local Object Transport Accelerator (LOTA) provides up to 7 GB/s of throughput per GPU
Source (primary)
CoreWeave Brings Up Multi-Rack NVIDIA Vera Rubin NVL72 Cluster - CoreWeave (-, news_article)
View cached copy (2026-09-19)Live source ↗
Quote: “LOTA provides up to 7 GB/s of throughput per GPU”
How we checked this
Checked on September 24, 2026. The cited source supports every part of this claim.
The press release states the 7 GB/s per-GPU figure for LOTA directly.
Confirmed in the source:
- LOTA (Local Object Transport Accelerator) is CoreWeave technology
- LOTA provides up to 7 GB/s of throughput per GPU
What we did: Read our cached copy of the publisher (https://www.coreweave.com/news/coreweave-brings-up-multi-rack-nvidia-vera-rubin-nvl72-cluster) in full (14,927 characters, retrieved September 19, 2026) and checked each assertion in the claim against it.
Additional evidence
confirms CoreWeave Brings Up Multi-Rack NVIDIA Vera Rubin NVL72 Cluster - CoreWeave
Quote: “LOTA provides up to 7 GB/s of throughput per GPU”