Tools tagged with "Cuda" – CodeRocket AI

AI Code Editor for GPU Kernel Mastery

AI Agents

+4 more

AI-powered editor for NVIDIA GPU kernels with real-time profiling, GPU emulation, and performance analysis.

Toolkit for compressing, deploying, and serving LLMs

LLMMLOps

LMDeploy is a toolkit for compressing, deploying, and serving LLMs. It provides efficient inference with TurboMind engine.

Dynamic Deep Learning Framework in Rust

Frameworks

Burn is a new comprehensive dynamic Deep Learning Framework built using Rust with extreme flexibility, compute efficiency, and portability.

Efficient ML in Rust, Simplified

Frameworks

Minimalist ML framework for Rust with GPU support and ease of use.

Accelerate AI with High-Performance Model Serving

LLMMLOps

Deliver low-latency, high-throughput inference for AI models. Supports diverse hardware and model types with extensive community backing.

Run LLMs Locally on Consumer GPUs

LLM

Fast inference library for local LLMs on consumer GPUs. Supports dynamic batching, smart caching, and more.

Optimize LLM Inference on NVIDIA GPUs

LLMMLOps

Enhance LLM performance with Python API and NVIDIA GPU optimizations for efficient inference.

Deploy AI Models Seamlessly Across Platforms

MLOps

Deploy AI models across frameworks with dynamic batching, real-time support, and cloud integration.

Accelerate LLM Training with Ease

LLMMLOps

Fine-tune and train LLMs faster with open-source tools. Beginner-friendly and efficient, supporting multiple GPUs.

Unlock Machine Learning Potential

Frameworks

Build and deploy ML models with ease using TensorFlow's robust ecosystem.

Unlock Deep Learning Potential

Frameworks

Join the PyTorch community for cutting-edge deep learning tools and resources. Enhance your projects with robust libraries and cloud support.