NeurIPS2019

November 27, 2019

Thanks to those who joined us at NeurIPS2019 to see Gaudi and Goya live demonstrations, workshop and more

Learn More

GOYA Inference on BERT

August 15, 2019

Goya outperforms T4 on key NLP inference benchmark

See the data

Habana Gaudi and Goya:
New levels of AI performance, low power
and cost efficiency for datacenter & cloud

Purpose-Built for AI Training

The only AI processor with Integrated RDMA
over Converged Ethernet to provide scalability
and lower total cost of ownership.

For more information about Gaudi

Purpose-Built for AI Inference

15,453 images-per-second throughput on ResNet-50

For more information about Goya

News & Events

Intel pledges $1 million in support of efforts to address social injustice and anti-racism

Read Intel CEO’s memo

Intel acquires Habana Labs.

Read the announcement

MLPerf reports Goya performance in industry’s first published inference benchmarks

Read the blog

Industry standards like Glow benefit data center and cloud customers.

See the blog.

Join us at Linley Processor Conference this Fall.

Habana takes the stage with industry leaders at AI Hardware Summit

Goya delivers 1,527 sentences-per-second on BERT NLP model.

See the details.

Thank you Hot Chips 31!

"Startup Projects to Hit Nvidia V100 Performance at Half the Power." Linley Group

CRN names Habana among Top 10 Coolest Machine Learning and AI startups of 2019.

See the details.

Check out Habana's presence at the O'Reilly AI Conference in Beijing

Learn more.

100% AI

Gain Performance:

Train Faster at
Ethernet Scale:

NeurIPS2019

GOYA Inference on BERT

Habana Gaudi and Goya:
New levels of AI performance, low power
and cost efficiency for datacenter & cloud

Purpose-Built for AI Training

Purpose-Built for AI Inference

Intel pledges $1 million in support of efforts to address social injustice and anti-racism

Intel acquires Habana Labs.

MLPerf reports Goya performance in industry’s first published inference benchmarks

Industry standards like Glow benefit data center and cloud customers.

Join us at Linley Processor Conference this Fall.

Habana takes the stage with industry leaders at AI Hardware Summit

Goya delivers 1,527 sentences-per-second on BERT NLP model.

Thank you Hot Chips 31!

"Startup Projects to Hit Nvidia V100 Performance at Half the Power." Linley Group

CRN names Habana among Top 10 Coolest Machine Learning and AI startups of 2019.

Check out Habana's presence at the O'Reilly AI Conference in Beijing

Habana Goya Inference Processor is the first AI processor to implement and open source the Glow compiler backend.

Follow us:

100% AI

Gain Performance:

Train Faster at Ethernet Scale:

NeurIPS2019

GOYA Inference on BERT

Habana Gaudi and Goya: New levels of AI performance, low power and cost efficiency for datacenter & cloud

Purpose-Built for AI Training

Purpose-Built for AI Inference

Intel pledges $1 million in support of efforts to address social injustice and anti-racism

Intel acquires Habana Labs.

MLPerf reports Goya performance in industry’s first published inference benchmarks

Industry standards like Glow benefit data center and cloud customers.

Join us at Linley Processor Conference this Fall.

Habana takes the stage with industry leaders at AI Hardware Summit

Goya delivers 1,527 sentences-per-second on BERT NLP model.

Thank you Hot Chips 31!

"Startup Projects to Hit Nvidia V100 Performance at Half the Power." Linley Group

CRN names Habana among Top 10 Coolest Machine Learning and AI startups of 2019.

Check out Habana's presence at the O'Reilly AI Conference in Beijing

Habana Goya Inference Processor is the first AI processor to implement and open source the Glow compiler backend.

Train Faster at
Ethernet Scale:

Habana Gaudi and Goya:
New levels of AI performance, low power
and cost efficiency for datacenter & cloud