This article explores Meta's Llama 2 large language model—its performance, expanded training data, architectural details, evaluation results, RLHF fine‑tuning process, and step‑by‑step deployment on UCloud UK8S using Docker and Kubernetes—providing a comprehensive guide for AI practitioners.
This guide walks you through using Alibaba Cloud's PAI platform to quickly fine‑tune Llama 2 with LoRA or full‑parameter methods, deploy the models as online inference services, and launch an interactive WebUI, covering preparation, data formatting, training jobs, and deployment details.
This tutorial walks you through preparing a VKE cluster, pulling the Langchain‑ChatGLM container image, creating the necessary Deployment and Service resources, and adding a local knowledge base, enabling you to run a Langchain‑based ChatGLM service with GPU support on Volcengine’s cloud‑native platform.
This article explains how Shuhe Technology leveraged Alibaba Cloud's Serverless Kubernetes (ASK) and Knative to deploy, scale, and monitor over 500 AI model services—including Stable Diffusion—achieving 60% cost savings, zero‑to‑scale elasticity, and rapid deployment cycles.
Deploy Stable Diffusion on Tencent Cloud by building a Docker image, pushing it to TCR, creating a GPU‑enabled TKE cluster with CFS storage, configuring qGPU sharing, exposing the service via Cloud Native API Gateway, optimizing inference with TACO Kit, storing results in COS, and applying content moderation.
This guide shows how to map a Stable Diffusion container's dynamic paths to Alibaba Cloud NAS, configure Serverless Devs, deploy the application, and upload model files via a visual admin UI or NAS commands, enabling fast AI image generation on a cloud‑native platform.
This guide walks you through deploying the open‑source Stable Diffusion WebUI on Alibaba Cloud Function Compute using Serverless Devs, covering prerequisites, a single‑line deployment command, configuration details, access URL, and practical tips for handling GPU rendering and cold‑start latency.
This article details Du Xiaoman's development of the ATLAS automated machine learning platform, covering business scenarios, AI algorithm deployment challenges, the end‑to‑end production workflow, platform components such as annotation, data, training and deployment, as well as optimization techniques like AutoML, meta‑learning, NAS, and large‑scale parallelism, concluding with lessons learned and future directions.
FastDeploy is an open‑source toolkit that standardizes AI model APIs and enables developers to deploy vision, NLP, and speech models on diverse hardware—including GPUs, CPUs, Jetson, ARM, and various NPUs—using just three lines of code or a single command, while delivering end‑to‑end performance optimizations.
The article presents PaddlePaddle’s PP‑ShiTu‑based smart retail product recognition solution, detailing a complete pipeline—from data preparation and model optimization to low‑latency deployment—that overcomes high‑similarity packaging, rapid SKU changes, and costly retraining, achieving over 98 % Top‑1 recall with 0.2‑second CPU inference.
With the rapid rise of edge computing, deploying AI models for tasks like object detection, OCR, and speech recognition on resource‑constrained devices faces speed challenges; the upgraded Paddle Lite inference engine and PaddleSlim compression tools claim up to 23% faster inference and significant model size reductions, offering a practical solution.
Alibaba’s MNN, a lightweight high‑performance deep‑learning inference engine, earned top honors in China’s 2022 “Science & Innovation China” awards, and delivers impressive gains such as 350% speedup on X86 CPUs, 2.1‑2.3× acceleration on ARM with sparse models, plus integrated OpenCV/Numpy functionality for edge AI deployment.
The article shares a programmer's interview experience at Baidu, discussing how to adapt AI algorithms for edge deployment, balance model performance and efficiency, apply model compression techniques, and continuously iterate models, while also promoting an upcoming AI deployment online course.
By moving decoding, color conversion, preprocessing, inference, and re‑encoding entirely onto the GPU and enabling batch processing with flexible Python scripts, iQIYI’s video‑image enhancement service achieved ten‑fold throughput, over 90 % GPU utilization, and dramatically lower resource use, accelerating AI video inference deployment.
This article shares personal journeys of five Huawei AI experts, recommends essential AI books, walks through setting up PyCharm with ModelArts for hands‑on model training, and outlines a three‑stage AI career roadmap—from practical coding to mastering principles and deploying inference—offering actionable guidance for anyone looking to break into artificial intelligence.
This article explains how to deploy TensorFlow on Kubernetes, addressing resource isolation, GPU scheduling, and distributed training challenges by introducing a custom TensorFlow‑on‑K8s system with client, task, and autospec modules, plus container design for reliable job execution.