-
🔭 I’m currently working on multi-modal machine learning and dimensionality reduction techniques.
-
🌱 I’m learning programming Hetergenous Parallel Systems, focusing on CUDA and Triton for efficient machine learning implementations.
-
🤔 I’m open to help with model distillation, quantization and efficient training and deployment of large ML models.
-
- Developing and optimizing multi-modal model architectures with scalable data input processing to enhance performance in distributed environments.
- Streamlining model training, fine-tuning, and inference processes for seamless integration with cloud and edge computing interfaces.
- Implementing hardware- and IO-aware ML model compression techniques to optimize inference efficiency and reduce computational overhead.
- AU
Highlights
- Pro
Pinned Loading
-
kernelheim
kernelheim PublicKernelHeim – development ground of custom Triton and CUDA kernel functions designed to optimize and accelerate machine learning workloads on NVIDIA GPUs. Inspired by the mythical stronghold of the …
Python 2
-
semantic-search
semantic-search PublicImplementation of semantic search using Sentence-BERT (SBERT) for a workshop. It demonstrates how to generate sentence embeddings and perform search based on cosine similarity, allowing for meaning…
Jupyter Notebook
-
classification-real-fake-text
classification-real-fake-text PublicClassifying real and fake text using metrics measuring human-written and machine-generated text
Jupyter Notebook 1
-
deep-learning-project-template
deep-learning-project-template Public templateForked from Lightning-AI/deep-learning-project-template
Pytorch Lightning code guideline for conferences
Python
-
cuda-mode-lectures
cuda-mode-lectures PublicForked from gpu-mode/lectures
Material for cuda-mode lectures
Jupyter Notebook 1
If the problem persists, check the GitHub status page or contact support.