From 0cb11961536ec1698dde18d95715840b2f28790b Mon Sep 17 00:00:00 2001 From: Jason Andrews Date: Fri, 29 May 2026 16:54:00 -0500 Subject: [PATCH 1/2] pre-publish review --- .wordlist.txt | 17 +++++++++++++++++ content/install-guides/memgraph-on-arm.md | 4 ++-- .../1-overview-and-setup.md | 4 ++-- .../3-run-inference.md | 4 ++-- .../4-benchmarking.md | 2 +- .../layouts/stats/list.html | 4 ---- 6 files changed, 24 insertions(+), 11 deletions(-) diff --git a/.wordlist.txt b/.wordlist.txt index 5e942b6374..b9f2ac1df2 100644 --- a/.wordlist.txt +++ b/.wordlist.txt @@ -6205,3 +6205,20 @@ Antigravity Moby antigravity callout +Cypher +Marek +Mayne +Memgraph +Memgraph’s +Micha +NetworkX +PageRank +RedHatAI +Sabika +TPOT +TTFT +Tasneem +cypher +memgraph +mgconsole +owski \ No newline at end of file diff --git a/content/install-guides/memgraph-on-arm.md b/content/install-guides/memgraph-on-arm.md index 46974382c3..5360c79ada 100644 --- a/content/install-guides/memgraph-on-arm.md +++ b/content/install-guides/memgraph-on-arm.md @@ -97,7 +97,7 @@ The following are Docker images that you can choose depending on the Memgraph fe | `memgraph/mgconsole` | Standalone CLI client. | | `memgraph/lab` | Memgraph Lab web UI. | -Start with `memgraph/memgraph` to get the Memgraph database. If you later want PageRank, community detection, node embeddings, NetworkX integration, or other advanced query modules, see the [MAGE section](#install-the-mage-graph-algorithm-library). +Start with `memgraph/memgraph` to get the Memgraph database. If you later want PageRank, community detection, node embeddings, NetworkX integration, or other advanced query modules, see the [MAGE section](#optional-install-the-mage-graph-algorithm-library). ### Connect with mgconsole inside the container @@ -117,7 +117,7 @@ Quit the shell by typing Ctrl-D(eof) or :quit memgraph> ``` -For example `mgconsole` queries, see the [example queries](#how-do-i-run-example-cypher-queries) section. +For example `mgconsole` queries, see the [example queries](#run-example-cypher-queries-through-mgconsole) section. ## Install Memgraph natively on Linux diff --git a/content/learning-paths/servers-and-cloud-computing/vllm-benchmark-quantisation/1-overview-and-setup.md b/content/learning-paths/servers-and-cloud-computing/vllm-benchmark-quantisation/1-overview-and-setup.md index db9f7aa20b..9d27621e4f 100644 --- a/content/learning-paths/servers-and-cloud-computing/vllm-benchmark-quantisation/1-overview-and-setup.md +++ b/content/learning-paths/servers-and-cloud-computing/vllm-benchmark-quantisation/1-overview-and-setup.md @@ -12,7 +12,7 @@ layout: learningpathall ## Understand the models you'll use -You'll use LLama 3.1 8B and Whisper large V3 in this Learning Path. +You'll use Llama 3.1 8B and Whisper large V3 in this Learning Path. Llama 3.1 8B is an open-weight, text-only LLM with 8 billion parameters that can understand and generate text. You can view the model card at https://huggingface.co/meta-llama/Llama-3.1-8B. @@ -68,7 +68,7 @@ pip install https://github.com/vllm-project/vllm/releases/download/v${VLLM_VERSI If you want to build vLLM from source, follow the instructions in the [Build and Run vLLM on Arm Servers Learning Path](/learning-paths/servers-and-cloud-computing/vllm/vllm-setup/). -### Set up access to LLama3.1-8B models +### Set up access to Llama3.1-8B models To access the Llama models hosted by Hugging Face, install the Hugging Face CLI and authenticate with your access token. Install the CLI: ```bash diff --git a/content/learning-paths/servers-and-cloud-computing/vllm-benchmark-quantisation/3-run-inference.md b/content/learning-paths/servers-and-cloud-computing/vllm-benchmark-quantisation/3-run-inference.md index f682e6e3e6..9d24afc9c5 100644 --- a/content/learning-paths/servers-and-cloud-computing/vllm-benchmark-quantisation/3-run-inference.md +++ b/content/learning-paths/servers-and-cloud-computing/vllm-benchmark-quantisation/3-run-inference.md @@ -6,7 +6,7 @@ weight: 4 layout: learningpathall --- -## Run inference on LLama3.1-8B +## Run inference on Llama3.1-8B vLLM serves an OpenAI-compatible API that you'll use to run inference on Llama3.1-8B and confirm that the local environment is set up correctly. @@ -260,6 +260,6 @@ The quantized Whisper model completes the same transcription in roughly a quarte ## What you've accomplished and what's next -You've now installed vLLM and run inference on your LLama and Whisper models. You've seen speedups in task completion between quantized and non-quantized models. +You've now installed vLLM and run inference on your Llama and Whisper models. You've seen speedups in task completion between quantized and non-quantized models. Next, you'll benchmark the Llama models and compare their performance. diff --git a/content/learning-paths/servers-and-cloud-computing/vllm-benchmark-quantisation/4-benchmarking.md b/content/learning-paths/servers-and-cloud-computing/vllm-benchmark-quantisation/4-benchmarking.md index 5e60cf7870..70b444c6d8 100644 --- a/content/learning-paths/servers-and-cloud-computing/vllm-benchmark-quantisation/4-benchmarking.md +++ b/content/learning-paths/servers-and-cloud-computing/vllm-benchmark-quantisation/4-benchmarking.md @@ -202,6 +202,6 @@ Run without `--limit` for a statistically representative accuracy comparison. ## What you've accomplished -You've now successfully benchmarked quantized and non-quantized LLama 3.1 8B models for throughput and accuracy. The results suggest that quantization improves a model's throughput but can reduce its accuracy. +You've now successfully benchmarked quantized and non-quantized Llama 3.1 8B models for throughput and accuracy. The results suggest that quantization improves a model's throughput but can reduce its accuracy. Now that your environment is set up for running inference, benchmarking, and quantizing different models, you can experiment further. Try benchmarking accuracy with different tasks, different quantization techniques, or different models. Your results will allow you to balance accuracy and performance when making decisions about model deployment. diff --git a/themes/arm-design-system-hugo-theme/layouts/stats/list.html b/themes/arm-design-system-hugo-theme/layouts/stats/list.html index ebd8bffb14..a6a294d49e 100644 --- a/themes/arm-design-system-hugo-theme/layouts/stats/list.html +++ b/themes/arm-design-system-hugo-theme/layouts/stats/list.html @@ -175,10 +175,6 @@

Authors

} - -