Insights
A Technical Deep Dive into Pipeline Parallel Inference with CentML
With yesterday’s release of Llama-3.1-405B, we’re excited to announce that CentML’s recent contribution to vLLM, adding pipeline parallel inference support, […]
![How to profile a Hugging Face model with DeepView](https://centml.ai/wp-content/uploads/2024/03/Hugging-Face-main-image-1-1-900x505.png)
How to profile a Hugging Face model with DeepView
Hugging Face has become a leading platform for natural language processing (NLP) and machine learning (ML) enthusiasts. It provides a […]
![Introducing DeepView: Visualize your neural network performance](https://centml.ai/wp-content/uploads/2024/02/Deep-View-main-image-900x505.jpg)
Introducing DeepView: Visualize your neural network performance
Optimize PyTorch neural networks, peak performance, and cost efficiency for your deep learning projects
![Maximizing LLM training and inference efficiency using CentML on OCI](https://centml.ai/wp-content/uploads/2023/11/OCI-CentML-header-3-1-900x505.png)
Maximizing LLM training and inference efficiency using CentML on OCI
In partnership with CentML, Oracle has developed innovative solutions to meet the growing demand for high-performance NVIDIA GPUs for machine […]
![GenAI company cuts training costs by 36% with CentML](https://centml.ai/wp-content/uploads/2024/02/Throughput_improvement-graph-1-1-900x505.png)
GenAI company cuts training costs by 36% with CentML
A growing generative AI company partnered with CentML to accelerate their API-as-a-service and iterate with foundational models—all without using top-of-the-line […]
![Hardware Efficiency in the Era of LLM Deployments](https://centml.ai/wp-content/uploads/2024/04/Hardware_Efficiency_img-900x505.jpg)
Hardware Efficiency in the Era of LLM Deployments
How CServe can make LLM deployment easy, efficient and scalable