Logo
IPU Inference Toolkit Quick Start
Version: latest
  • 1. 概述
    • 1.1. IPU推理方案架构
  • 2. 模型编译
    • 2.1. 模型下载
    • 2.2. 模型转换和编译
  • 3. 模型运行
    • 3.1. 通过PopRT Runtime运行
      • 3.1.1. 环境准备
      • 3.1.2. 使用 Python API 运行模型
      • 3.1.3. 通过 C++ API 运行模型
    • 3.2. 部署模型到Triton Inference Server
      • 3.2.1. 生成模型的配置
      • 3.2.2. 启动模型服务
      • 3.2.3. 通过gRPC验证服务
  • 4. Trademarks & copyright
IPU Inference Toolkit Quick Start

Search help

Note: Searching from the top-level index page will search all documents. Searching from a specific document will search only that document.

  • Find an exact phrase: Wrap your search phrase in "" (double quotes) to only get results where the phrase is exactly matched. For example "PyTorch for the IPU" or "replicated tensor sharding"
  • Prefix query: Add an * (asterisk) at the end of any word to indicate a prefix query. This will return results containing all words with the specific prefix. For example tensor*
  • Fuzzy search: Use ~N (tilde followed by a number) at the end of any word for a fuzzy search. This will return results that are similar to the search word. N specifies the “edit distance” (fuzziness) of the match. For example Polibs~1
  • Words close to each other: ~N (tilde followed by a number) after a phrase (in quotes) returns results where the words are close to each other. N is the maximum number of positions allowed between matching words. For example "ipu version"~2
  • Logical operators. You can use the following logical operators in a search:
    • + signifies AND operation
    • | signifies OR operation
    • - negates a single word or phrase (returns results without that word or phrase)
    • () controls operator precedence

IPU Inference Toolkit Quick Start

  • 1. 概述
    • 1.1. IPU推理方案架构
  • 2. 模型编译
    • 2.1. 模型下载
    • 2.2. 模型转换和编译
  • 3. 模型运行
    • 3.1. 通过PopRT Runtime运行
      • 3.1.1. 环境准备
      • 3.1.2. 使用 Python API 运行模型
      • 3.1.3. 通过 C++ API 运行模型
    • 3.2. 部署模型到Triton Inference Server
      • 3.2.1. 生成模型的配置
      • 3.2.2. 启动模型服务
      • 3.2.3. 通过gRPC验证服务
  • 4. Trademarks & copyright
下一页

修订 9db9a47e.