From 8bf079892fb4bf5f43780b59711459e137931f1e Mon Sep 17 00:00:00 2001 From: Jeremy Eder Date: Mon, 6 May 2024 03:44:19 +0000 Subject: [PATCH 1/2] add component list and optimize image tag step Signed-off-by: Jeremy Eder --- README.md | 25 ++++++++++++++----------- 1 file changed, 14 insertions(+), 11 deletions(-) diff --git a/README.md b/README.md index 462491b..4d564d6 100644 --- a/README.md +++ b/README.md @@ -13,6 +13,15 @@ simplification, as well as a broadening of capabilities, hardware and software support versions, performance improvements (and other optimizations) prior to GA. +RHEL AI is an open-source product that includes: + +- [Granite](https://huggingface.co/instructlab): an open source, Apache 2 licensed foundation model from IBM. +- [InstructLab](https://github.com/instructlab): a CLI and tuning backend that provides a simple user interface for contributing knowledge and skills to a base model. +- [RHEL Image Mode (bootc)](https://github.com/containers/bootc): RHEL AI is distributed as a “bootable container” image. Provision RHEL AI appliances via kickstart onto bare metal or cloud instances. +- [vLLM](https://github.com/vllm-project/vllm): A high-throughput and memory-efficient inference and serving engine for LLMs, based on PyTorch. +- [deepspeed](https://www.deepspeed.ai/): A deep learning optimization software suite for both training and inference. +- [PyTorch](https://pytorch.org/): PyTorch is an optimized tensor library for deep learning using GPUs and CPUs. + > [!NOTE] > RHEL AI is targeted at server platforms and workstations with discrete GPUs. > For laptops, please use upstream [InstructLab](https://github.com/instructlab). @@ -157,24 +166,18 @@ Image-mode “bootable” container. We embed the 3 images above into this container. ```sh -make nvidia FROM=registry.redhat.io/rhel9/rhel-bootc:9.4 +make nvidia FROM=registry.redhat.io/rhel9/rhel-bootc:9.4 REGISTRY= REGISTRY_ORG= ``` -The resulting image is tagged `quay.io/rhelai-dev-preview/nvidia-bootc:latest`. +The resulting image is tagged `${REGISTRY}/${REGISTRY_ORG}/nvidia-bootc:latest`. For more variables and examples, see the [training/README](https://github.com/rhelai-dev-preview/tree/main/training). -Tag your image with your registry name and path: - -```sh -podman tag quay.io//nvidia-bootc:latest quay.io//nvidia-bootc:latest -``` - -Push the resulting image to your registry. You will refer to this URL inside a -kickstart file in an upcoming step. +Push the resulting image to your registry. You will refer to this URL inside a kickstart file in an upcoming step. ```sh -podman push quay.io//nvidia-bootc:latest +podman push ${REGISTRY}/${REGISTRY_ORG}/nvidia-bootc:latest +e.g. podman push quay.io//nvidia-bootc.latest ``` > At this point you have a RHEL AI bootable container image ready to be installed on a physical or virtual host. From 7a70eb7a4dedb0b554d289b6ef72d79f938fcbac Mon Sep 17 00:00:00 2001 From: Russell Bryant Date: Mon, 6 May 2024 10:39:15 -0600 Subject: [PATCH 2/2] Update dictionary for spellcheck Signed-off-by: Russell Bryant --- .spellcheck-en-custom.txt | 2 ++ 1 file changed, 2 insertions(+) diff --git a/.spellcheck-en-custom.txt b/.spellcheck-en-custom.txt index bb73aa5..dfee435 100644 --- a/.spellcheck-en-custom.txt +++ b/.spellcheck-en-custom.txt @@ -49,6 +49,7 @@ codebases compositional Conala Corbett +CPUs curation cybette danmcp @@ -60,6 +61,7 @@ datasets dave DCO De +deepspeed deployable DeSaix dev