Note: Searching from the top-level index page will search all documents. Searching from a specific document will search only that document.
"" (double quotes) to only get results where the phrase is exactly matched. For example "PyTorch for the IPU" or "replicated tensor sharding"* (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*~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~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+ signifies AND operation| signifies OR operation- negates a single word or phrase (returns results without that word or phrase)() controls operator precedenceIPU推理工具包旨在提供低延时高性能的端到端推理解决方案，使用户能够方便快速的部署模型到Graphcore IPU产品上。
本文将涵盖以下内容:
介绍Graphcore的软件栈，以及模型的编译和运行时架构。
介绍IPU所需的硬件和系统，以及如何通过容器启动一个IPU环境并确认其状态正常。
以ONNX、TensorFlow和PyTorch的模型为例，阐述如何通过工具将不同框架导出的模型转换为运行在IPU上的PopEF。
讲述如何通过PopRT Runtime API运行PopEF，以及如何通过Triton Inference Server和TensorFlow Serving部署PopEF。
介绍如何使用IPU推理工具包部署一个在线搜索解决方案。
介绍GPU/IPU混合部署的解决方案。
关于在Kubernetes集群中部署的信息，请参考 Kubernetes IPU Device Plugin User Guide 。
备注
关于如何获取本文中使用的容器镜像，请联系 Graphcore Sales 。