Perspectives for Direct Interpretability in Multi-Agent Deep Reinforcement Learning
Paper
•
2502.00726
•
Published
•
1
AI & ML interests
None defined yet.
Xmaster6y
authored
a
paper
3 months ago
Post
2742
It will be very interesting to benchmark how energy-efficient the new Falcon-Edge is: https://huggingface.co/blog/tiiuae/falcon-edge
Should be super efficient on CPU according to the numbers published for BitNet: https://github.com/microsoft/BitNet/blob/main/assets/intel_performance.jpg
Should be super efficient on CPU according to the numbers published for BitNet: https://github.com/microsoft/BitNet/blob/main/assets/intel_performance.jpg
- 1 reply
Sckathach
authored
a
paper
10 months ago
Post
1776
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...
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...
Post
1043
Nice to see day 1 support of Falcon 3 on Gaudi with Optimum Habana!
👉 https://www.intel.com/content/www/us/en/developer/articles/technical/intel-ai-solutions-support-falcon-3-fdn-models.html
👉 https://www.intel.com/content/www/us/en/developer/articles/technical/intel-ai-solutions-support-falcon-3-fdn-models.html
benkoska
authored
a
paper
about 1 year ago
Post
1434
Interested in performing inference with an ONNX model?⚡️
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:
Check out the whole guide 👉 https://huggingface.co/docs/optimum/onnxruntime/usage_guides/models
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 👉 https://huggingface.co/docs/optimum/onnxruntime/usage_guides/models
VaultChem
updated
a
Space
about 1 year ago
jeremyzacch
updated
a
Space
about 1 year ago
nizarzerouale
updated
a
Space
about 1 year ago
Mojmir
updated
a
Space
about 1 year ago
WenqingZhang
updated
a
Space
about 1 year ago
TomSmail
updated
a
Space
about 1 year ago
tagny
updated
a
Space
about 1 year ago
Sckathach
updated
a
Space
about 1 year ago
micpst
updated
a
Space
about 1 year ago
n-schuldt
updated
a
Space
about 1 year ago
lukalafaye
updated
2
Spaces
about 1 year ago
Nos7
updated
a
Space
about 1 year ago