# Together AI — Introducing Together Storage Accelerator: fast, free data caching for your GPU cluster

- Company: Together AI (together.ai)
- Announced: 2026-11-19
- Category: infrastructure-release
- Coverage: not counted
- Announcement: yes
- Group: announcements
- Source: https://www.together.ai/blog/introducing-together-storage-accelerator
- Record: https://forck.live/items/38917-introducing-together-storage-accelerator-fast-free-data-caching-for-your-gpu
- Subject: Inference platform
- Pricing: included free with every Together GPU Cluster

Together AI is launching Together Storage Accelerator, a distributed caching layer for Together GPU Clusters that caches data on cluster NVMe so repeated reads from object storage and Hugging Face Hub are served locally. The company says the problem is that every cold start pays a WAN tax, with cross-cloud reads slow, rate-limited and expensive, and egress from AWS running up to $0.09/GB. Measured on an H100 node, Together reports warm reads about 20x faster than a cross-cloud origin at up to 3.4 GB/s per node, with a 2 GiB object that took 13-15 s from Cloudflare R2 read from cache in 0.6-0.7 s. Cold reads cost nothing extra, the first read through TSA running within about 5% of a direct download, and a 70 GB checkpoint pulled by 200 nodes fetches from the source once instead of 200 times. TSA needs no application changes: existing boto3 code, transformers calls and CLI workflows work as-is, with credentials encrypted in a secrets vault. It is available now on Together GPU Clusters at no additional cost, enabled from the cluster's Settings page, and works with any S3-compatible store including Together's T4 object storage, which is in limited preview.

## Evidence

Verbatim from https://www.together.ai/blog/introducing-together-storage-accelerator:

> A distributed cache on every GPU node: about 20x faster warm reads, one origin fetch per cluster, and no application changes. Included free with Together GPU Clusters.
> 
> Authors
> 
> Pavneet Ahluwalia, Vinamra Jain
> 
> Table of contents
> 
> 40+ Models Chosen for Production...40+ Models Chosen for Production...40+ Models Chosen for Production...
> 
> Your GPUs are only as fast as your data pipelines. Every training run that starts with a 30-minute model download, every node that re-pulls the same dataset from across the country, and every Hugging Face rate limit that stalls a job leads to compute resources sitting idle, waiting for your data, while you are paying for them.
> 
> Today we're launching Together Storage Accelerator (TSA) , a distributed caching layer for Together GPU Clusters that alleviates the need for repeated data reads from object storage and Hugging Face Hub, dramatically accelerating your AI data pipelines while also cutting your data egress bills. TSA is now included free with every Together GPU Cluster.
> 
> The problem: your data lives far from your GPUs

---

Record: https://forck.live/items/38917-introducing-together-storage-accelerator-fast-free-data-caching-for-your-gpu
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md
