Ilyas Moutawwakil's picture

Ilyas Moutawwakil

IlyasMoutawwakil

AI & ML interests

Optimization, LLMs, Hardware, Backends, ..

Recent Activity

updated a dataset 8 days ago
optimum-benchmark/cuda
updated a dataset 8 days ago
optimum-benchmark/misc-windows-latest-3.8
updated a dataset 8 days ago
optimum-benchmark/cpu
View all activity

Articles

Organizations

Hugging Face's profile picture Training Transformers Together's profile picture OpenVINO Toolkit's profile picture ONNXConfig for all's profile picture Hugging Face Optimum's profile picture HugGAN Community's profile picture HuggingFaceM4's profile picture Hugging Face H4's profile picture Optimum AMD's profile picture That Time I got Reincarnated as a Hugging Face Organization's profile picture AI Energy Score Project's profile picture Optimum-Benchmark's profile picture Social Post Explorers's profile picture Optimum-Intel's profile picture Hugging Face Machine Learning Optimization's profile picture Optimum Internal Testing's profile picture

Posts 1

view post
Post
3993
Last week, Intel's new Xeon CPUs, Sapphire Rapids (SPR), landed on Inference Endpoints and I think they got the potential to reduce the cost of your RAG pipelines 💸

Why ? Because they come with Intel® AMX support, which is a set of instructions that support and accelerate BF16 and INT8 matrix multiplications on CPU ⚡

I went ahead and built a Space to showcase how to efficiently deploy embedding models on SPR for both Retrieving and Ranking documents, with Haystack compatible components: https://huggingface.co./spaces/optimum-intel/haystack-e2e

Here's how it works:

- Document Store: A FAISS document store containing the seven-wonders dataset, embedded, indexed and stored on the Space's persistent storage to avoid unnecessary re-computation of embeddings.

- Retriever: It embeds the query at runtime and retrieves from the dataset N documents that are most semantically similar to the query's embedding.
We use the small variant of the BGE family here because we want a model that's fast to run on the entire dataset and has a small embedding space for fast similarity search. Specifically we use an INT8 quantized bge-small-en-v1.5, deployed on an Intel Sapphire Rapids CPU instance.

- Ranker: It re-embeds the retrieved documents at runtime and re-ranks them based on semantic similarity to the query's embedding. We use the large variant of the BGE family here because it's optimized for accuracy allowing us to filter the most relevant k documents that we'll use in the LLM prompt. Specifically we use an INT8 quantized bge-large-en-v1.5, deployed on an Intel Sapphire Rapids CPU instance.

Space: https://huggingface.co./spaces/optimum-intel/haystack-e2e
Retriever IE: optimum-intel/fastrag-retriever
Ranker IE: optimum-intel/fastrag-ranker