NVIDIA Triton Inference Server
NVIDIA Triton™ inference server delivers fast and scalable AI in production. Open-source inference serving software, Triton inference server streamlines AI inference by enabling teams deploy trained AI models from any framework (TensorFlow, NVIDIA TensorRT®, PyTorch, ONNX, XGBoost, Python, custom and more on any GPU- or CPU-based infrastructure (cloud, data center, or edge). Triton runs models concurrently on GPUs to maximize throughput and utilization, supports x86 and ARM CPU-based inferencing, and offers features like dynamic batching, model analyzer, model ensemble, and audio streaming. Triton helps developers deliver high-performance inference aTriton integrates with Kubernetes for orchestration and scaling, exports Prometheus metrics for monitoring, supports live model updates, and can be used in all major public cloud machine learning (ML) and managed Kubernetes platforms. Triton helps standardize model deployment in production.
Learn more
Wafer
Wafer delivers the fastest open source LLMs for enterprise through serverless and dedicated inference built for production AI workloads. Its serverless inference gives teams access to top open models with no infrastructure, no deployment overhead, and fast APIs, including GLM-5.2-Fast for low-latency inference with EAGLE speculative decoding and a per-stream throughput SLA, GLM-5.2 as a flagship model with stronger coding and reasoning capabilities, and more. Wafer’s technology uses agents that optimize inference across the stack, identifying and enhancing bottlenecks in orchestration, algorithms, serving engines, GPU kernels, and diverse hardware. It profiles the stack to see whether latency or throughput comes from scheduling, decoding, kernels, memory pressure, or hardware fit, then tries many paths and ships the measured winner. Instead of relying on a single switch or heuristic, Wafer searches model, engine, kernel, and hardware combinations.
Learn more
NVIDIA TensorRT
NVIDIA TensorRT is an ecosystem of APIs for high-performance deep learning inference, encompassing an inference runtime and model optimizations that deliver low latency and high throughput for production applications. Built on the CUDA parallel programming model, TensorRT optimizes neural network models trained on all major frameworks, calibrating them for lower precision with high accuracy, and deploying them across hyperscale data centers, workstations, laptops, and edge devices. It employs techniques such as quantization, layer and tensor fusion, and kernel tuning on all types of NVIDIA GPUs, from edge devices to PCs to data centers. The ecosystem includes TensorRT-LLM, an open source library that accelerates and optimizes inference performance of recent large language models on the NVIDIA AI platform, enabling developers to experiment with new LLMs for high performance and quick customization through a simplified Python API.
Learn more
vLLM
vLLM is a high-performance library designed to facilitate efficient inference and serving of Large Language Models (LLMs). Originally developed in the Sky Computing Lab at UC Berkeley, vLLM has evolved into a community-driven project with contributions from both academia and industry. It offers state-of-the-art serving throughput by efficiently managing attention key and value memory through its PagedAttention mechanism. It supports continuous batching of incoming requests and utilizes optimized CUDA kernels, including integration with FlashAttention and FlashInfer, to enhance model execution speed. Additionally, vLLM provides quantization support for GPTQ, AWQ, INT4, INT8, and FP8, as well as speculative decoding capabilities. Users benefit from seamless integration with popular Hugging Face models, support for various decoding algorithms such as parallel sampling and beam search, and compatibility with NVIDIA GPUs, AMD CPUs and GPUs, Intel CPUs, and more.
Learn more