tchaton84

Lightning.ai – production managed inference platform for AI

Posted by tchaton84 on Thursday October 09, 2025 @10:34AM
from the artificialanalysis.ai dept.

https://artificialanalysis.ai/models/llama-3-3-instruct-70b/providers

( Read More... | 1 comment | 2 points | on HN )

Re:Lightning.ai – production managed inference platform for AI on Thursday October 09, 2025 @10:34AM (#45528274)

After making model training simpler with PyTorch Lightning, Lightning.AI is now tackling the next bottleneck — inference. Their new managed service targets enterprises deploying LLMs and deep learning models at scale, emphasizing performance, cost-efficiency, and developer-friendly tooling.

Platform: https://lightning.ai/

Re:Deploy dedicated DeepSeek 32B on L40 GPUs ($8/hour) on Saturday February 01, 2025 @03:35PM (#42901988)

Does it support largest Deepseek model ?

Lightning Data: Blazingly fast, distributed streaming of data from cloud storage

Posted by tchaton84 on Friday February 23, 2024 @05:33PM
from the github.com dept.

https://github.com/Lightning-AI/litdata

( Read More... | 1 comment | 9 points | on HN )

Re:Lightning Data: Blazingly fast, distributed streaming of data from ... on Friday February 23, 2024 @05:33PM (#39487000)

Blazingly fast, distributed streaming of training data from cloud storage. PyTorch & PyTorch Lightning compatible.

Re: on Wednesday January 31, 2024 @03:07PM (#39208679)

1 click reproducible environment to prepare TinyLlama project dataset