SqueezeBits

SqueezeBits compresses AI models using state-of-the-art techniques including quantization, pruning, knowledge distillation, and AutoML, enabling clients to gain access to software stacks for building and computing energy-efficient, lightweight and fast deep learning models on various hardware platforms from edge devices to cloud GPUs.

GPU


Funding Amount: $1.90M

Funding Type: Pre Series A

Funding Date: 2024-01-23

City & State: Seoul, Seoul-t'ukpyolsi

Country South Korea

Employee Count: 11


Unlock founder details & tech stack data with a premium subscription.

Similar Startups

RunPod
RunPod Logo

RunPod is a cloud platform designed for GPUs, enabling developers to deploy customized full-stack AI applications. RunPod is dedicated to ensuring that cloud computing remains accessible and affordable while maintaining its full range of features, usability, and user experience. Its mission is to empower individuals and enterprises withstate-of-the-art technology, allowing them to harness the power of AI and cloud computing to their fullest potential.

Activeloop
Activeloop Logo

Activeloop automatically connects unstructured data to machine learning models and offers data streaming, scalable machine learning pipelines, and dataset version control for distributed workloads, enabling deep learning teams to access, visualize, and improve their datasets to build great models.

Taalas
Taalas Logo

Taalas provides automated flow for quickly implementing specialized chips that can each run different AI models by using hard-wired computation and allows a single chip to outperform a small GPU data center, which could decrease the cost of AI hardware development, enabling the AI industry to achieve an improvement in computational power and efficiency, and efficiently running powerful models locally on any consumer device.

Lambda
Lambda Logo

Lambda is a deep-learning infrastructure company, that provides computation to accelerate human progress. The company's cloud technology, servers, and workstations are pre-configured with common ML frameworks, enabling clients to simplify and accelerate the training and deployment of deep learning models.