Skip to content
View jac-76's full-sized avatar

Block or report jac-76

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
jac-76/README.md

Hi, I'm Joseph Austin Chasar 👋

Self-taught Linux engineer working close to the hardware — kernel modules, systemd, udev, core-dump debugging — currently focused on running AI locally on AMD Ryzen AI NPU silicon, and on making that stack reproducible.

What I've built

  • npu-container — the whole NPU inference stack in a container: digest-pinned reproducible build, a preflight/verification harness, GitHub Actions CI, and Kubernetes manifests.
  • local-ai-assistant — a fully offline voice assistant on the NPU: mic → Whisper ASR → on-NPU LLM → piper TTS. Stdlib-only Python.
  • npu-whisper — one-shot Whisper transcription on the NPU (Bash, zero dependencies) plus a RAPL power/latency benchmark harness. Measured RTF ≈ 0.17 and ~10× lower energy per transcription than the same model on CPU.

Write-up: Running Whisper + LLMs on an AMD NPU under Linux — the amdxdna / XRT driver stack, the one real gotcha (memlock), the runtime that skips the Windows-only SDK, and benchmarks you can reproduce.

Stack: Linux internals · Python · Bash · Ryzen AI / XDNA2 · FastFlowLM · Docker · GitHub Actions · systemd / udev / DKMS · Git

Learning: Kubernetes in anger · Terraform · AWS

Open to junior MLOps / DevOps / SRE / Linux / backend-Python roles. 📫 jac-76@live.com · 🌐 jac-76.github.io

Pinned Loading

  1. jac-76.github.io jac-76.github.io Public

    Personal site — self-taught Linux engineer running Whisper + LLMs on AMD Ryzen AI NPU hardware. Built with a stdlib-only Markdown renderer.

    HTML

  2. local-ai-assistant local-ai-assistant Public

    Fully offline voice assistant running on the AMD Ryzen AI NPU: mic → Whisper ASR → on-NPU LLM → piper TTS. Stdlib-only Python.

    Python

  3. npu-container npu-container Public

    Containerized AMD Ryzen AI NPU inference stack — reproducible digest-pinned Docker build, verification harness, CI, and Kubernetes manifests.

    Python

  4. npu-whisper npu-whisper Public

    Whisper ASR on the AMD Ryzen AI NPU — zero-dependency Bash wrapper over FastFlowLM, plus a RAPL power/latency benchmark harness. RTF ≈ 0.17.

    Python