A technical walkthrough shows how to use vLLM to load multiple LoRA adapters for role‑playing LLMs, analyzes the massive GPU and labor costs of naïve deployment, and presents a hosted multi‑LoRA platform as a cost‑effective solution.
This article reviews ten mainstream LLM deployment solutions—including WebLLM, LM Studio, Ollama, vLLM, LightLLM, OpenLLM, HuggingFace TGI, GPT4ALL, llama.cpp, and Triton Inference Server—detailing their technical characteristics, strengths, drawbacks, and example deployment workflows for both personal and enterprise environments.
The article provides a detailed technical analysis of Nvidia’s new GB300 and B300 GPUs, comparing their performance, memory architecture, and power consumption to previous generations, and examines how these changes affect AI inference workloads, NVL72 accelerator systems, and the supply‑chain strategies of major cloud providers.
This article explains how Kubernetes’ native scalability, resource optimization, performance tuning, portability, and fault‑tolerance features align with the demands of AI inference, helping organizations run large ML models efficiently, cost‑effectively, and reliably across diverse environments.
This article explores how compact multimodal models like OmniVision-968M enable efficient generative AI on edge devices, detailing their architectural advantages, benchmark superiority over larger models, and step‑by‑step instructions for local installation and visual inference using NexaSDK.
This article explains the fundamentals of Retrieval‑Augmented Generation (RAG), its four‑step workflow, architecture, and how Intel’s hardware and software optimizations—including vector search, quantized embeddings, and advanced inference extensions—enhance performance, security, and scalability for enterprise LLM applications.
AI inferenceEmbedding QuantizationIntel Optimization
The 5th China Cloud Computing Infrastructure Developer Conference in Beijing highlighted cutting‑edge AI inference optimization, Knative‑based serverless acceleration, AMD PMU virtualization, and CDI‑driven GPU management, offering detailed technical insights and real‑world case studies that illustrate how cloud providers are tackling performance and cost challenges of modern workloads.
This article details a comprehensive engineering practice for optimizing AI inference services at ZhiZhuan, covering background analysis, selection of TorchServe over alternatives, GPU/CPU performance tuning, custom handlers, Torch‑TRT integration, and deployment on Kubernetes, with measured improvements in throughput and resource utilization.
Kubernetes aligns perfectly with AI inference demands by offering built‑in scalability, resource and performance optimization, seamless portability across clouds, and robust fault‑tolerance, making it a cost‑effective, high‑availability foundation for deploying large‑scale machine‑learning models.
This article explains what a GPU is, how it differs from a CPU, its internal architecture, and why its massive parallel processing makes it essential for graphics rendering, scientific computation, and AI inference, illustrated with examples such as NVIDIA RTX 3090.
This guide walks through enabling KServe on Alibaba Cloud ASM, preparing the Llama‑2‑7B model with TensorRT‑LLM, creating the necessary Kubernetes resources, and deploying a serverless AI inference service that can be queried via a simple curl request.
This tutorial walks through deploying the Llama‑2‑7b‑hf model on Alibaba Cloud Kubernetes (ACK) using KServe, Triton Inference Server with the TensorRT‑LLM backend, covering prerequisites, model preparation, YAML configuration, PV/PVC setup, runtime creation, and troubleshooting steps.
The article describes how JD’s advertising team tackled the high‑concurrency, low‑latency challenges of online recommendation inference by designing a distributed graph heterogeneous computing framework, optimizing GPU kernel launches with TensorBatch, deep‑learning compiler techniques, and a multi‑stream GPU architecture, achieving significant throughput and latency improvements.
AI inferenceDeep Learning CompilerGPU optimization
This guide walks you through setting up a Conda Python environment, installing PyTorch and the ModelScope library, running NLP pipelines for tasks like word segmentation and text classification, and calling ModelScope models from PHP using the PHPY extension, complete with code examples and troubleshooting tips.
This guide walks through installing Anaconda, creating a Python 3.10 conda environment, adding PyTorch and ModelScope libraries, installing domain-specific dependencies, verifying NLP pipelines, and using PHPY to call ModelScope's OCR model from PHP, complete with code snippets and troubleshooting tips.
LocalAI is an open‑source, cost‑effective alternative to the ChatGPT API that lets you download and run thousands of language models locally via Docker or compiled binaries, offering privacy, customization, and easy integration into projects through a compatible API.
SAMP is an adaptive mixed-precision inference toolkit that automatically controls floating-point and integer operations to accelerate model inference while maintaining computational accuracy.
AI inferenceNLP accelerationmixed-precision computing
This article explains how LMDeploy streamlines the deployment of Hugging Face transformer models by adding online conversion, offering an OpenAI‑compatible API server, a Gradio WebUI, and 4‑bit weight‑only quantization with AWQ, providing step‑by‑step commands, code examples, and performance insights.
The article presents SenseTime's PPL framework, detailing its toolchain, inference engine, multi‑backend operator library, quantization tools, CUDA optimizations, performance benchmarks across CPUs, GPUs, DSPs and DSAs, and outlines future plans for broader chip support and AI for Science.
AI inferenceCUDA optimizationDeep Learning Deployment
Bilibili’s self‑developed InferX framework, combined with NVIDIA Triton Inference Server, streamlines AI model serving by adding quantization, structured sparsity, and custom kernels, delivering up to eight‑fold throughput gains, cutting GPU usage by half, and enabling faster, cost‑effective OCR and large‑model deployments.
The article describes Punica, a cloud‑native, function‑as‑a‑service platform that unifies content‑understanding inference services through a one‑stop portal and unattended operations, improving deployment speed, resource utilization, and reducing manual effort for AI model serving.
The Punica system unifies AI inference development, testing, deployment, and maintenance on a FaaS‑based one‑stop platform that automates resource scheduling, self‑healing, and monitoring, supporting multiple frameworks and GPUs, thereby doubling onboarding speed, quintuple scaling efficiency, and reclaiming hundreds of GPU cards.
AI inferenceAutonomous OperationsFaaS architecture
Punica provides a cloud‑native, one‑stop platform that unifies Baidu’s content‑understanding inference services, automates testing, resource provisioning, and monitoring, and enables unattended, self‑healing operations with dynamic scaling and GPU scheduling, cutting onboarding time by half and reclaiming hundreds of GPUs.
This article provides an end‑to‑end analysis of AI inference bottlenecks, reviews common industry acceleration techniques, and details Baidu Intelligent Cloud’s AIAK‑Inference suite—including its architecture, optimization strategies such as model pruning, operator fusion, and single‑operator tuning—followed by a demo showing significant latency reductions on ResNet‑50 and other models.
This article presents a comprehensive analysis of AI inference bottlenecks, explores industry acceleration techniques such as model simplification, operator fusion, and single‑operator optimization, and details Baidu Cloud's AIAK‑Inference suite with practical demos showing up to 90% latency reduction.
This article details the evolution of 58 Tongcheng's deep learning inference platform—from the initial WPAI‑based architecture to a cloud‑native, Istio‑powered design—covering its background, technical challenges, architectural redesign, traffic‑management features, adaptive rate limiting, model warm‑up, and observability improvements.
The article details vivo's development of a high‑accuracy, high‑performance streaming speech‑recognition inference engine built on the wenet framework, its optimization techniques such as dynamic batching and memory pooling, collaborative acceleration with KunlunChip's high‑performance inference library, and extensive performance benchmarks demonstrating multi‑batch GPU and XPU gains.
Tencent’s hardware teams evolved from a lack of verification tools in 2019 to building AI inference chips, video‑encoding silicon, and intelligent NICs, overcoming FPGA challenges, scaling cloud infrastructure, and delivering high‑performance, low‑cost solutions for massive multimedia and AI workloads.
This talk explains how Ant Group’s frontend engineers built edge‑AI services that run directly in browsers, boosting real‑time performance, preserving privacy, and cutting cloud costs, while showcasing two real‑world cases—pet identification and screen‑break insurance—and detailing the WebGL‑based engine optimizations that lifted device coverage from 30% to 93%.
The article explains how to design a C++‑based multithreaded service that uses Pthreads, channels, and TensorRT to parallelize deep‑learning inference tasks, thereby reducing latency and dramatically increasing throughput for AI applications such as facial‑recognition access control systems.
Michael Yuan’s ServerlessDays China 2021 talk shows how combining Rust with WebAssembly on Tencent Cloud Serverless lets developers deploy TensorFlow AI models in just a few lines, achieving 10‑20 fps inference, 100× faster cold starts than Python, and offering lightweight, secure, portable runtimes that could eventually supplant containers for edge and AI workloads.
This article introduces TensorRT, explains its deployment workflow from model training to engine generation, shows how to register custom operators for ONNX and create TensorRT plugins, and explores deformable convolution (DCN) implementation strategies for high‑performance AI inference.
iQIYI created a custom GPU‑virtual‑sharing system that intercepts CUDA calls to enforce per‑container memory limits, rewrites kernel launches for compute isolation, and integrates with a Kubernetes scheduler extender, allowing multiple AI inference containers to share a single V100 with minimal overhead and more than doubling overall GPU utilization.
Alibaba Cloud's Zhenduan heterogeneous computing acceleration platform achieved historic breakthroughs in the MLPerf inference benchmark, processing over 1.07 million images per second on 8 NVIDIA A100 GPUs, setting multiple first‑place records and dramatically improving e‑commerce recommendation speed and overall AI workload efficiency.
The article introduces Didi’s IFX platform, describing its background, four‑layer architecture (access, software, engine, compute), productization efforts such as high‑performance optimizations, model and engine compression, unified deployment across hardware, multi‑framework support, automation, and security enhancements, and concludes with future plans.
DiDi’s IFX AI inference platform, built since 2018, uses a four‑layer architecture spanning access, software, engine, and compute to deliver cloud, edge, and device inference with high‑performance kernel optimizations, model and binary compression, uniform multi‑framework deployment, automated testing, and end‑to‑end security for billions of daily calls.
This article examines the challenges of deep learning inference, outlines general optimization methodologies—including system-level and model-level techniques—presents practical case studies such as Transformer translation model improvements, and discusses future trends in automated compilation and performance tuning for AI services.
dl_inference is an open‑source inference platform that simplifies deployment of TensorFlow and PyTorch models in production, offering unified gRPC access, load‑balanced multi‑node serving, GPU/CPU options, customizable pre‑ and post‑processing, and extensible architecture for future AI workloads.
Didi’s Elastic Inference Service (EIS) and its IFX AI acceleration engine provide a distributed, cost‑effective inference platform that automatically scales resources based on QPS and latency requirements, supports major deep‑learning frameworks, excels in public‑cloud, private‑cloud, IoT and edge scenarios, and achieved top‑rank DAWNBench latency and cost scores on ImageNet with P4 GPUs.
This article explains the design of ACE (AI Labs Compute Engine), a heterogeneous edge compute platform that combines model quantization, GPU/DSP/VPU acceleration, cloud‑edge model management, and custom algorithm integration to enable low‑latency AI services such as gesture, pet, and pen‑tip detection on resource‑constrained devices.
This article presents a comprehensive overview of a universal FPGA‑based CNN accelerator, detailing its motivation, flexible architecture, compiler workflow, memory and compute unit designs, and performance comparisons that demonstrate significant latency and cost advantages over CPU and GPU solutions for real‑time AI inference.