Average Ratings 0 Ratings
Average Ratings 0 Ratings
Description
Featuring up to 8 NVidia® H100 80GB GPUs, each equipped with 16896 CUDA cores and 528 Tensor Cores, this represents NVidia®'s latest flagship technology, setting a high standard for AI performance. The system utilizes the SXM5 NVLINK module, providing a memory bandwidth of 2.6 Gbps and enabling peer-to-peer bandwidth of up to 900GB/s. Additionally, the fourth generation AMD Genoa processors support up to 384 threads with a boost clock reaching 3.7GHz. For NVLINK connectivity, the SXM4 module is employed, which boasts an impressive memory bandwidth exceeding 2TB/s and a P2P bandwidth of up to 600GB/s. The second generation AMD EPYC Rome processors can handle up to 192 threads with a boost clock of 3.3GHz. The designation 8A100.176V indicates the presence of 8 RTX A100 GPUs, complemented by 176 CPU core threads and virtualized capabilities. Notably, even though it has fewer tensor cores compared to the V100, the architecture allows for enhanced processing speeds in tensor operations. Moreover, the second generation AMD EPYC Rome is also available with configurations supporting up to 96 threads and a boost clock of 3.35GHz, further enhancing the system's performance capabilities. This combination of advanced hardware ensures optimal efficiency for demanding computational tasks.
Description
NVIDIA TensorRT is a comprehensive suite of APIs designed for efficient deep learning inference, which includes a runtime for inference and model optimization tools that ensure minimal latency and maximum throughput in production scenarios. Leveraging the CUDA parallel programming architecture, TensorRT enhances neural network models from all leading frameworks, adjusting them for reduced precision while maintaining high accuracy, and facilitating their deployment across a variety of platforms including hyperscale data centers, workstations, laptops, and edge devices. It utilizes advanced techniques like quantization, fusion of layers and tensors, and precise kernel tuning applicable to all NVIDIA GPU types, ranging from edge devices to powerful data centers. Additionally, the TensorRT ecosystem features TensorRT-LLM, an open-source library designed to accelerate and refine the inference capabilities of contemporary large language models on the NVIDIA AI platform, allowing developers to test and modify new LLMs efficiently through a user-friendly Python API. This innovative approach not only enhances performance but also encourages rapid experimentation and adaptation in the evolving landscape of AI applications.
API Access
Has API
API Access
Has API
Integrations
CUDA
Dataoorts GPU Cloud
Hugging Face
Kimi K2
LaunchX
MATLAB
NVIDIA AI Enterprise
NVIDIA Clara
NVIDIA DRIVE
NVIDIA DeepStream SDK
Integrations
CUDA
Dataoorts GPU Cloud
Hugging Face
Kimi K2
LaunchX
MATLAB
NVIDIA AI Enterprise
NVIDIA Clara
NVIDIA DRIVE
NVIDIA DeepStream SDK
Pricing Details
$3.01 per hour
Free Trial
Free Version
Pricing Details
Free
Free Trial
Free Version
Deployment
Web-Based
On-Premises
iPhone App
iPad App
Android App
Windows
Mac
Linux
Chromebook
Deployment
Web-Based
On-Premises
iPhone App
iPad App
Android App
Windows
Mac
Linux
Chromebook
Customer Support
Business Hours
Live Rep (24/7)
Online Support
Customer Support
Business Hours
Live Rep (24/7)
Online Support
Types of Training
Training Docs
Webinars
Live Training (Online)
In Person
Types of Training
Training Docs
Webinars
Live Training (Online)
In Person
Vendor Details
Company Name
DataCrunch
Country
Finland
Website
datacrunch.io
Vendor Details
Company Name
NVIDIA
Founded
1993
Country
United States
Website
developer.nvidia.com/tensorrt