{"batchcomplete":"","continue":{"lecontinue":"20260507230748|1823","continue":"-||"},"query":{"logevents":[{"logid":1833,"ns":0,"title":"Hugo","pageid":1937,"logpage":1937,"params":{},"type":"create","action":"create","user":"Busk","timestamp":"2026-06-01T15:07:51Z","comment":"Created page with \"``` nohup hugo server --source website_hugo --disableFastRender > hugo-server.log 2>&1 & ```\""},{"logid":1832,"ns":0,"title":"Amdgpu rocm","pageid":1936,"logpage":1936,"params":{},"type":"create","action":"create","user":"Busk","timestamp":"2026-05-26T02:23:14Z","comment":"Created page with \"# Make sure keyring dir exists sudo mkdir --parents --mode=0755 /etc/apt/keyrings  # Refresh AMD key, same as you already did wget https://repo.radeon.com/rocm/rocm.gpg.key -O...\""},{"logid":1831,"ns":0,"title":"Rocm","pageid":1935,"logpage":1935,"params":{},"type":"create","action":"create","user":"Busk","timestamp":"2026-05-26T02:04:13Z","comment":"Created page with \"https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/install-methods/package-manager/package-manager-ubuntu.html\""},{"logid":1830,"ns":0,"title":"Zfs optimization","pageid":1934,"logpage":1934,"params":{},"type":"create","action":"create","user":"Busk","timestamp":"2026-05-25T15:56:52Z","comment":"Created page with \"# ZFS Optimization Get & Set  ## Get current settings for pool ``` #!/bin/bash  if [ -z \"$1\" ]; then     echo \"Usage: $0 <pool_name>\"     exit 1 fi  POOL=\"$1\"  if ! zpool list...\""},{"logid":1829,"ns":0,"title":"Codex use local openai api","pageid":1933,"logpage":1933,"params":{},"type":"create","action":"create","user":"Busk","timestamp":"2026-05-22T15:57:28Z","comment":"Created page with \"To point the **Codex CLI** to your local `llama-server`, you primarily need to override the environment variables that the tool uses to locate the OpenAI API.  Since the Codex...\""},{"logid":1828,"ns":0,"title":"Zfs nvme log and cache","pageid":1932,"logpage":1932,"params":{},"type":"create","action":"create","user":"Busk","timestamp":"2026-05-22T15:36:45Z","comment":"Created page with \"``` sudo nvme list Node                  Generic               SN                   Model                                    Namespace  Usage                      Format...\""},{"logid":1827,"ns":0,"title":"Llama optimization","pageid":1931,"logpage":1931,"params":{},"type":"create","action":"create","user":"Busk","timestamp":"2026-05-13T17:32:49Z","comment":"Created page with \"Yes, that is a good **stable baseline**:  ```bash ./build/bin/llama-server \\   -hf ggml-org/gpt-oss-20b-GGUF \\   -ngl 999 \\   -c 2048 \\   -np 1 \\   -t 8 \\   --no-warmup \\   --...\""},{"logid":1826,"ns":0,"title":"Llama 1","pageid":1930,"logpage":1930,"params":{},"type":"create","action":"create","user":"Busk","timestamp":"2026-05-13T16:32:10Z","comment":"Created page with \"`model.gguf` was just a placeholder. You need to download an actual `.gguf` file, such as:  ```text gpt-oss-20b-mxfp4.gguf ```  For GPT-OSS 20B, the Hugging Face repo is:  ```...\""},{"logid":1825,"ns":0,"title":"Tesla P40 llama.cpp","pageid":1929,"logpage":1929,"params":{},"type":"create","action":"create","user":"Busk","timestamp":"2026-05-13T16:19:32Z","comment":"Created page with \"``` sudo apt update sudo apt install -y git cmake build-essential curl libcurl4-openssl-dev  git clone https://github.com/ggml-org/llama.cpp cd llama.cpp  cmake -B build -DGGM...\""},{"logid":1824,"ns":0,"title":"Tesla P40","pageid":1928,"logpage":1928,"params":{},"type":"create","action":"create","user":"Busk","timestamp":"2026-05-13T16:16:18Z","comment":"Created page with \" You must reboot after update so in kernel   ```bash nvidia-srv/580.126.20, 6.8.0-111-generic, x86_64: installed ```  I would **stay on `580-server`** for the Tesla P40.  Do *...\""}]}}