Habana AI

company
Activity Feed

AI & ML interests

Habana Labs was founded in 2016 to create world-class AI Processors, developed from the ground-up and optimized for training deep neural networks and for inference deployment in production environments.

Habana's activity

jeffboudierย 
posted an update 9 days ago
jeffboudierย 
posted an update 14 days ago
regisssย 
posted an update 23 days ago
jeffboudierย 
posted an update 24 days ago
view post
Post
2575
Transcribing 1 hour of audio for less than $0.01 ๐Ÿคฏ

@mfuntowicz cooked with 8x faster Whisper speech recognition - whisper-large-v3-turbo transcribes at 100x real time on a $0.80/hr L4 GPU!

How they did it: https://huggingface.co/blog/fast-whisper-endpoints

1-click deploy with HF Inference Endpoints: https://endpoints.huggingface.co/new?repository=openai%2Fwhisper-large-v3-turbo&vendor=aws&region=us-east&accelerator=gpu&instance_id=aws-us-east-1-nvidia-l4-x1&task=automatic-speech-recognition&no_suggested_compute=true
jeffboudierย 
posted an update about 1 month ago
jeffboudierย 
posted an update 2 months ago
view post
Post
2204
Llama4 is out and Scout is already on the Dell Enterprise Hub to deploy on Dell systems ๐Ÿ‘‰ dell.huggingface.co
jeffboudierย 
posted an update 2 months ago
view post
Post
1565
Enterprise orgs now enable serverless Inference Providers for all members
- includes $2 free usage per org member (e.g. an Enterprise org with 1,000 members share $2,000 free credit each month)
- admins can set a monthly spend limit for the entire org
- works today with Together, fal, Novita, Cerebras and HF Inference.

Here's the doc to bill Inference Providers usage to your org: https://huggingface.co/docs/inference-providers/pricing#organization-billing
  • 2 replies
ยท
regisssย 
posted an update 4 months ago
view post
Post
1755
Nice paper comparing the fp8 inference efficiency of Nvidia H100 and Intel Gaudi2: An Investigation of FP8 Across Accelerators for LLM Inference (2502.01070)

The conclusion is interesting: "Our findings highlight that the Gaudi 2, by leveraging FP8, achieves higher throughput-to-power efficiency during LLM inference"

One aspect of AI hardware accelerators that is often overlooked is how they consume less energy than GPUs. It's nice to see researchers starting carrying out experiments to measure this!

Gaudi3 results soon...
regisssย 
in Habana/mamba 4 months ago

Upload 2 files

3
#3 opened 4 months ago by
zzhang37
jeffboudierย 
posted an update 5 months ago
view post
Post
751
NVIDIA just announced the Cosmos World Foundation Models, available on the Hub: nvidia/cosmos-6751e884dc10e013a0a0d8e6

Cosmos is a family of pre-trained models purpose-built for generating physics-aware videos and world states to advance physical AI development.
The release includes Tokenizers nvidia/cosmos-tokenizer-672b93023add81b66a8ff8e6

Learn more in this great community article by @mingyuliutw and @PranjaliJoshi https://huggingface.co/blog/mingyuliutw/nvidia-cosmos
  • 1 reply
ยท
regisssย 
posted an update 6 months ago
regisssย 
in Habana/mamba 6 months ago

Upload 2 files

#2 opened 6 months ago by
zzhang37

Upload 2 files

2
#1 opened 6 months ago by
zzhang37
jeffboudierย 
posted an update 7 months ago
regisssย 
posted an update 8 months ago
view post
Post
1425
Interested in performing inference with an ONNX model?โšก๏ธ

The Optimum docs about model inference with ONNX Runtime is now much clearer and simpler!

You want to deploy your favorite model on the hub but you don't know how to export it to the ONNX format? You can do it in one line of code as follows:
from optimum.onnxruntime import ORTModelForSequenceClassification

# Load the model from the hub and export it to the ONNX format
model_id = "distilbert-base-uncased-finetuned-sst-2-english"
model = ORTModelForSequenceClassification.from_pretrained(model_id, export=True)

Check out the whole guide ๐Ÿ‘‰ https://huggingface.co/docs/optimum/onnxruntime/usage_guides/models
jeffboudierย 
posted an update 8 months ago
jeffboudierย 
posted an update 9 months ago
view post
Post
474
Inference Endpoints got a bunch of cool updates yesterday, this is my top 3
jeffboudierย 
posted an update 9 months ago
view post
Post
4114
Pro Tip - if you're a Firefox user, you can set up Hugging Chat as integrated AI Assistant, with contextual links to summarize or simplify any text - handy!

In this short video I show how to set it up
ยท