diff --git a/.wordlist.txt b/.wordlist.txt index 5afe320b18..a8093169d0 100644 --- a/.wordlist.txt +++ b/.wordlist.txt @@ -4559,7 +4559,7 @@ qdisc ras rcu regmap -rgerganov’s +rgerganov's rotocol rpcgss rpmh @@ -4588,3 +4588,6 @@ vmscan workqueue xdp xhci +JFR +conv +servlet \ No newline at end of file diff --git a/content/learning-paths/embedded-and-microcontrollers/_index.md b/content/learning-paths/embedded-and-microcontrollers/_index.md index 8ee2672ec5..dc4f325370 100644 --- a/content/learning-paths/embedded-and-microcontrollers/_index.md +++ b/content/learning-paths/embedded-and-microcontrollers/_index.md @@ -49,7 +49,7 @@ tools_software_languages_filter: - Coding: 26 - Containerd: 1 - DetectNet: 1 -- Docker: 9 +- Docker: 10 - DSTREAM: 2 - Edge AI: 1 - Edge Impulse: 1 diff --git a/content/learning-paths/embedded-and-microcontrollers/visualizing-ethos-u-performance/2-overview.md b/content/learning-paths/embedded-and-microcontrollers/visualizing-ethos-u-performance/2-overview.md index 23997c19c6..b087e70934 100644 --- a/content/learning-paths/embedded-and-microcontrollers/visualizing-ethos-u-performance/2-overview.md +++ b/content/learning-paths/embedded-and-microcontrollers/visualizing-ethos-u-performance/2-overview.md @@ -28,7 +28,7 @@ TinyML is machine learning optimized to run on low-power, resource-constrained d This Learning Path focuses on using TinyML models with virtualized Arm hardware to simulate real-world AI workloads on microcontrollers and NPUs. -If you're looking to build and train your own TinyML models, follow the [Introduction to TinyML on Arm using PyTorch and ExecuTorch](/embedded-and-microcontrollers/introduction-to-tinyml-on-arm/). +If you're looking to build and train your own TinyML models, follow the [Introduction to TinyML on Arm using PyTorch and ExecuTorch](/learning-paths/embedded-and-microcontrollers/introduction-to-tinyml-on-arm/). ## What is ExecuTorch? diff --git a/content/learning-paths/embedded-and-microcontrollers/visualizing-ethos-u-performance/_index.md b/content/learning-paths/embedded-and-microcontrollers/visualizing-ethos-u-performance/_index.md index c8bc257324..0127cde363 100644 --- a/content/learning-paths/embedded-and-microcontrollers/visualizing-ethos-u-performance/_index.md +++ b/content/learning-paths/embedded-and-microcontrollers/visualizing-ethos-u-performance/_index.md @@ -32,7 +32,7 @@ operatingsystems: tools_software_languages: - Arm Virtual Hardware - - Fixed Virtual Platform (FVP) + - Fixed Virtual Platform - Python - PyTorch - ExecuTorch diff --git a/content/learning-paths/servers-and-cloud-computing/_index.md b/content/learning-paths/servers-and-cloud-computing/_index.md index 878d7bd782..792fa14883 100644 --- a/content/learning-paths/servers-and-cloud-computing/_index.md +++ b/content/learning-paths/servers-and-cloud-computing/_index.md @@ -47,7 +47,7 @@ tools_software_languages_filter: - ASP.NET Core: 2 - Assembly: 4 - assembly: 1 -- Async-profiler: 1 +- async-profiler: 1 - AWS: 1 - AWS CDK: 2 - AWS CodeBuild: 1 diff --git a/content/learning-paths/servers-and-cloud-computing/distributed-inference-with-llama-cpp/how-to-1.md b/content/learning-paths/servers-and-cloud-computing/distributed-inference-with-llama-cpp/how-to-1.md index 6838a42e06..51791d684e 100644 --- a/content/learning-paths/servers-and-cloud-computing/distributed-inference-with-llama-cpp/how-to-1.md +++ b/content/learning-paths/servers-and-cloud-computing/distributed-inference-with-llama-cpp/how-to-1.md @@ -10,7 +10,7 @@ layout: learningpathall The instructions in this Learning Path are for any Arm server running Ubuntu 24.04.2 LTS. You will need at least three Arm server instances with at least 64 cores and 128GB of RAM to run this example. The instructions have been tested on an AWS Graviton4 c8g.16xlarge instance ## Overview -llama.cpp is a C++ library that enables efficient inference of LLaMA and similar large language models on CPUs, optimized for local and embedded environments. Just over a year ago from its publication date, rgerganov’s RPC code was merged into llama.cpp, enabling distributed inference of large LLMs across multiple CPU-based machines—even when the models don’t fit into the memory of a single machine. In this learning path, we’ll explore how to run a 405B parameter model on Arm-based CPUs. +llama.cpp is a C++ library that enables efficient inference of LLaMA and similar large language models on CPUs, optimized for local and embedded environments. Just over a year ago from its publication date, rgerganov's RPC code was merged into llama.cpp, enabling distributed inference of large LLMs across multiple CPU-based machines—even when the models don’t fit into the memory of a single machine. In this learning path, we’ll explore how to run a 405B parameter model on Arm-based CPUs. For the purposes of this demonstration, the following experimental setup will be used: - Total number of instances: 3