×
Large Language Model

Best Practices for Large Model Inference in ACK: TensorRT-LLM

This article uses the Llama-2-7b-hf model as an example to demonstrate how to deploy the Triton framework using KServe in Alibaba Cloud ACK.

Analyzing the Distributed Inference Process Using vLLM and Ray from the Perspective of Source Code

This article explores how to implement distributed inference with vLLM and Ray from a source code perspective.

Alibaba AI Tool Creates Picture Books for Children with Autism

Over 50,000 people have used Alibaba's AI-powered tool to create picture books for children with autism since it launched in June 2024.

การปรับใช้โมเดลภาษาขนาดใหญ่ของ Alibaba Cloud (Tongy Qianwen) ด้วยส่วนต่อประสานรายคำสั่งและกราฟิก

บทความนี้สำรวจสองวิธีในการโต้ตอบกับโมเดล Tongyi Qianwen-7B วิธีหนึ่งใช้ส่วนต่อประสานกราฟิกกับผู้ใช้(GUI) และอีกวิธีหนึ่งผ่านส่วนต่อประสานรายคำสั่ง (CL...

Alibaba Cloud’s Qwen2 with Enhanced Capabilities Tops LLM Leaderboard

The latest language model series from Alibaba Cloud topped rankings for open-sourced LLMs thanks to enhanced performance and safety alignment.

Redefines Luxury Retail Experience in China with a New Extended Partnership with Alibaba

LVMH Group and Alibaba Group announced an extended partnership to push further the boundary of luxury experience in China through AI-powered innovations in retail and on-line with Tmall.

จุดประกายปฏิวัติ AI - การเดินทางร่วมกับ RAG และ LangChain

บทความนี้จะพาผู้อ่านไปสำรวจเจาะลึกเกี่ยวกับเส้นทางการปฏิวัติ AI โดยเจาะลึกแนวคิดการปฏิวัติของ Retrieval-Augmented Generation (RAG) และ LangChain

Learning about AIACC-Training | Use AIACC-Training for TensorFlow

This article describes how to use AIACC-Training for TensorFlow.

Learning about AIACC-Training | Startup Commands and Environment Variables

This article describes the startup commands and the environment variables in AIACC-Training.

Learning about AIACC-Training | Use AIACC-Training for MXNet

This article describes how to use AIACC-Training for MXNet.

Learning about AIACC-Training | Use AIACC-Training for PyTorch

This article describes how to use AIACC-Training to accelerate distributed training by using models that are built based on PyTorch.

Learning about AIACC-Training | Install AIACC-Training

This article describes how to install AIACC-Training 1.5.0.

Accelerating Large Language Model Inference: High-performance TensorRT-LLM Inference Practices

This article introduces how TensorRT-LLM improves the efficiency of large language model inference by using quantization, in-flight batching, attention, and graph rewriting.

Chinese Automaker FAW Group Taps Alibaba Cloud’s Gen AI for Business Intelligence

Alibaba Cloud is partnering with FAW Group to transform the automaker‘s business intelligence capabilities with generative AI.

Solution 2: Build Your Llama2 LLM Solution with Compute Nest (ECS + AnalyticDB for PostgreSQL)

Explore the integration of AnalyticDB for PostgreSQL with large language models on Alibaba Cloud's Compute Nest, empowering businesses with efficiency.

Solution 1: Build Your Llama2 LLM Solution with PAI-EAS and AnalyticDB for PostgreSQL

Explore the integration of AnalyticDB for PostgreSQL with large language models on Alibaba Cloud's Compute Nest, empowering businesses with efficiency.

Solution 1B: How to Use ECS + PAI + AnalyticDB for PostgreSQL to Build a Llama2 Solution

Explore the integration of AnalyticDB for PostgreSQL with large language models on Alibaba Cloud's PAI, empowering businesses with efficiency.

Lightblue Releases Japanese-Language LLMs based on Qwen-14B for Commercial Use

Lightblue has released the most performant 14-billion parameter Japanese LLMs, suitable for on-premise commercial use.

Deploying Alibaba Cloud Large Language Model (Tongy Qianwen) with Graphical and Command Line Interfaces

In this blog, we will DeployAlibaba Cloud Large Language Model (Tongy Qianwen-7B) with Graphical and Command Line Interfaces

Alibaba's DAMO Academy Unveils LLMs Designed For Southeast Asia

DAMO Academy unveiled on Monday two large language models designed to reflect Southeast Asia's diverse linguistic and cultural landscape.