---
format: "aidr-story-markdown/v1"
id: "45937eaa27ceb8530924bdd839c733c9024b91a0c7a032c459e439b9dc51c913"
canonical_url: "https://aidr.today/45937eaa?lang=en"
title: "Modal Launches Multi Node Clusters for 1T Parameter Models"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-10-01T22:39:45.000Z"
category: "Infra"
topics: ["llm","agent"]
source_urls: ["https://huggingnews.com/ai/modal-launches-multi-node-clusters-for-1t-parameter-models-9691f494","https://marketbrief.now/ai/modal-launches-multi-node-clusters-for-1t-parameter-models-9691f494","https://huggingnews.com/ai/modal-launches-byoc-20-for-private-ai-agent-hosting-504ae782","https://marketbrief.now/ai/modal-launches-byoc-20-for-private-ai-agent-hosting-504ae782"]
summary: "← Back to live feed · 1 stories across 1 day Developers of artificial intelligence can now deploy and scale their workloads using an expanded set of infrastructure tools on the Modal platform. The general availability of multi-node clusters allows for the training of models with as many as 1T parameters, a scale already achieved by user Decagon. These clusters provide RDMA-connected nodes that are accessible instantly through a single decorator using the rdma=True configuration. The updates to Modal's Runtime also introduce VM sandboxes, sandbox sidecars, and sticky sessions to improve workload isolation and request routing. These tools enable high-performance distributed computing by providing developers with more control over how compute nodes are instantiated and managed."
---

# Modal Launches Multi Node Clusters for 1T Parameter Models

> [Open the canonical story](<https://aidr.today/45937eaa?lang=en>)

**Published:** 2026-10-01T22:39:45.000Z
**Category:** Infra
**Topics:** llm, agent

## Summary

← Back to live feed · 1 stories across 1 day Developers of artificial intelligence can now deploy and scale their workloads using an expanded set of infrastructure tools on the Modal platform\. The general availability of multi\-node clusters allows for the training of models with as many as 1T parameters, a scale already achieved by user Decagon\. These clusters provide RDMA\-connected nodes that are accessible instantly through a single decorator using the rdma\=True configuration\. The updates to Modal's Runtime also introduce VM sandboxes, sandbox sidecars, and sticky sessions to improve workload isolation and request routing\. These tools enable high\-performance distributed computing by providing developers with more control over how compute nodes are instantiated and managed\.

## Sources

- [Story source](<https://huggingnews.com/ai/modal-launches-multi-node-clusters-for-1t-parameter-models-9691f494>)
- [Story source](<https://marketbrief.now/ai/modal-launches-multi-node-clusters-for-1t-parameter-models-9691f494>)
- [Story source](<https://huggingnews.com/ai/modal-launches-byoc-20-for-private-ai-agent-hosting-504ae782>)
- [Story source](<https://marketbrief.now/ai/modal-launches-byoc-20-for-private-ai-agent-hosting-504ae782>)