Main

type

5

status

21

review version

1

cleanup version

2

pending deletion

0

created at

2024-07-31 14:17:23

updated at

2025-12-28 02:02:53

Address

url

https://leonardo.ai/news/leonardo-scales-image-captioning-with-the-nvidia-gh200/

url length

80

url crc

26121

url crc32

2395104777

location type

1

canonical status

2

canonical page id

-

Source

domain id

28657454

domain tld

660

domain parts

2

originating warc id

-

originating url

https://leonardo.ai/post-sitemap1.xml

source type

1

Server response

server ip

104.16.13.3

pubdate

2025-08-03 18:00:09

attempts

0

size orig

384626

size saved

73135

Content

page id

1783923615

title

Leonardo AI Scales Image Captioning with NVIDIA GH200 on Lambda

excerpt

content

Lambda provides cloud support for accelerating deep learning workflows vital to cutting edge generative technology. Leonardo AI is a startup creating and serving advanced text-to-image services & uses Lambda’s compute resources for their production systems and research programs for their flexibility and reliability. TL;DR  We captioned thirty million images from our internal dataset using CogVLM-17B on the NVIDIA GH200 architecture. The GH200 alleviates a communication bottleneck commonly seen in VRAM-limited A100-40GN nodes and allows us to reach a batch size that saturates GPU utilisation. Porting our existing captioning pipeline to the GH200 cluster configured by Lambda took only a day & improved throughput by over a factor of 3x. Throughput gains allow finer-grained synthetic captions, used to train more performant text-to-image models, ultimately creating better results at inference stage. The Benchmarked Task Our pipeline entails loading a batch of ...

author

updated

1767562614

Text analysis

block type

0

extracted fields

235

extracted bits

featured image
image author
title
full content
content was extracted heuristically
OpenGraph suggests this is an article

detected location

0

detected language

1 (English)

category id

-

index version

1

paywall score

0

spam phrases

0

Text statistics

text nonlatin

0

text cyrillic

0

text characters

3201

text words

607

text unique words

322

text lines

1

text sentences

24

text paragraphs

1

text words per sentence

25

text matched phrases

0

text matched dictionaries

0