Merge pull request #2147 from oracle-devrel/compute-review2025

review 2025

Author: Ainura-Djumagulov

cloud-infrastructure/compute-including-hpc/ai-infra-gpu/ai-infrastructure/README.md

@@ -2,7 +2,7 @@
 
 This repository contains detailed information related to Oracle Cloud Infrastructure GPU compute instances.
 
-Reviewed: 26.02.2024
+Reviewed: 16.10.202
 
 # Table of Contents
 

cloud-infrastructure/compute-including-hpc/ai-infra-gpu/ai-infrastructure/deepspeed-training-tuning/README.md

@@ -4,7 +4,7 @@ This repository provides a step-by-step deployment of DeepSpeed training for Lar
 
 This setup includes a tuned DeepSpeed configuration (`tuned_ds_config.json`) that provides up to **13% performance improvement** over standard configurations.
 
-Reviewed: 06.06.2025
+Reviewed: 16.10.2025
 # When to use this asset?
 
 Use this asset when you need to:

cloud-infrastructure/compute-including-hpc/ai-infra-gpu/ai-infrastructure/llm-benchmark-docker/README.md

@@ -7,7 +7,7 @@ and
 using
 [Docker Compose](https://docs.docker.com/compose/).
 
-Reviewed: 20.05.2025
+Reviewed: 16.10.2025
 
 # When should this asset be used?
 

cloud-infrastructure/compute-including-hpc/ai-infra-gpu/ai-infrastructure/nemo-megatron-training-oke/README.md

@@ -8,7 +8,7 @@ on the Oracle Container Engine for Kubernetes (OKE) using
 Reference results from NVIDIA to train Llama 3 can be found on the
 [NGC Catalog](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/dgxc-benchmarking/resources/llama3-dgxc-benchmarking).
 
-Reviewed: 01.07.2025
+Reviewed: 16.10.2025
 
 # When to use this asset?
 

cloud-infrastructure/compute-including-hpc/ai-infra-gpu/ai-infrastructure/nim-gpu-oke/README.md

@@ -4,7 +4,7 @@ This repository intends to demonstrate how to deploy [NVIDIA NIM](https://develo
 
 The model used is `Llama2-7B-chat`, running on an NVIDIA A10 Tensor Core GPU hosted on OCI. For scalability, we are hosting the model repository on a Bucket in Oracle Cloud Object Storage.
 
-Reviewed 23.05.2024
+Reviewed 16.10.2025
 
 # When to use this asset?
 

cloud-infrastructure/compute-including-hpc/ai-infra-gpu/ai-infrastructure/rag-langchain-vllm-mistral/README.md

@@ -2,7 +2,7 @@
 
 This repository is a variant of the Retrieval Augmented Generation (RAG) tutorial available [here](https://github.com/oracle-devrel/technology-engineering/tree/main/ai-and-app-modernisation/ai-services/generative-ai-service/rag-genai). Instead of the OCI GenAI Service, it uses a local deployment of Mistral 7B Instruct v0.3 using a vLLM inference server powered by an NVIDIA A10 GPU.
 
-Reviewed: 23.05.2024
+Reviewed: 16.10.2025
 
 # When to use this asset?
 

cloud-infrastructure/compute-including-hpc/ai-infra-gpu/ai-infrastructure/triton-gpu-oke/README.md

@@ -2,7 +2,7 @@
 
 This repository intends to demonstrate how to deploy NVIDIA Triton Inference Server on Oracle Kubernetes Engine (OKE) with TensorRT-LLM Backend in order to server Large Language Models (LLMs) in a Kubernetes architecture.
 
-Reviewed 23.05.2024
+Reviewed 16.10.2025
 
 # When to use this asset?
 

cloud-infrastructure/compute-including-hpc/ai-infra-gpu/ai-infrastructure/triton-mixtral/README.md

@@ -2,7 +2,7 @@
 
 This repository provides a step-by-step tutorial for deploying and using Mixtral 8x7B Large Language Model using the NVIDIA Triton Inference Server and the TensorRT-LLM backend.
 
-Reviewed: 23.05.2024
+Reviewed: 16.10.2025
 
 # When to use this asset?
 

cloud-infrastructure/compute-including-hpc/ai-infra-gpu/ai-infrastructure/vllm-mistral/README.md

@@ -2,7 +2,7 @@
 
 This repository provides a step-by-step tutorial for deploying and using [Mistral 7B Instruct](https://mistral.ai/technology/#models) Large Language Model using the [vLLM](https://github.com/vllm-project/vllm?tab=readme-ov-file) library.
 
-Reviewed: 23.05.2024
+Reviewed: 16.10.2025
 
 # When to use this asset?