popov/neuron-tai
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

md

Browse Source
This commit is contained in:
Dobromir Popov
2026-07-08 17:29:23 +02:00
parent 560de08edd
commit 7419ace926
1 changed files with 29 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

39
QUICKSTART.md
View File

@@ -7,28 +7,47 @@ Tested on: AMD Ryzen AI Max (Strix Halo APU), 124 GB RAM, Linux, CPU inference.
## Prerequisites ## Prerequisites
Choose the shell you will actually run `meshnet-*` from. Editable installs point
the command wrappers at this source tree, so normal code edits are picked up
without reinstalling.
**Linux / WSL**
```bash ```bash
# Clone and enter repo # Clone and enter repo
cd /run/media/popov/d/DEV/repos/d-popov.com/AI cd /run/media/popov/d/DEV/repos/d-popov.com/AI
# Create the virtualenv if it does not exist yet # Create the virtualenv if it does not exist yet
python3 -m venv .venv python3 -m venv .venv
source .venv/bin/activate
# Keep packaging tools current enough for editable installs # Keep packaging tools current enough for editable installs
.venv/bin/python -m pip install --upgrade pip setuptools wheel .venv/bin/python -m pip install --upgrade pip setuptools wheel
# Install Python packages (editable — picks up code changes immediately) # Install Python packages (editable — picks up code changes immediately)
.venv/bin/pip install -e packages/tracker -e packages/node -e packages/p2p -e packages/gateway -e packages/relay .venv/bin/python -m pip install -e packages/tracker -e packages/node -e packages/p2p -e packages/gateway -e packages/relay
# PyTorch: choose one
# CPU-only PyTorch (skip if you have CUDA/ROCm already) .venv/bin/python -m pip install torch
.venv/bin/pip install torch --index-url https://download.pytorch.org/whl/cpu # .venv/bin/python -m pip install torch --index-url https://download.pytorch.org/whl/cpu
# .venv/bin/python -m pip install torch --index-url https://download.pytorch.org/whl/rocm6.2
# HuggingFace model libraries # HuggingFace model libraries
.venv/bin/pip install "transformers>=5.12" accelerate .venv/bin/python -m pip install "transformers>=5.12" accelerate
``` ```
> **NVIDIA GPU (CUDA):** replace the torch line with `pip install torch` (default index). **Windows PowerShell**
> **AMD GPU (ROCm):** `pip install torch --index-url https://download.pytorch.org/whl/rocm6.2`
```powershell
cd D:\DEV\workspace\REPOS\git.d-popov.com\neuron-tai
python -m venv .venv
.\.venv\Scripts\Activate.ps1
.\.venv\Scripts\python.exe -m pip install --upgrade pip setuptools wheel
.\.venv\Scripts\python.exe -m pip install -e .\packages\tracker -e .\packages\node -e .\packages\p2p -e .\packages\gateway -e .\packages\relay
# PyTorch: choose one
.\.venv\Scripts\python.exe -m pip install torch
# .\.venv\Scripts\python.exe -m pip install torch --index-url https://download.pytorch.org/whl/cpu
# .\.venv\Scripts\python.exe -m pip install torch --index-url https://download.pytorch.org/whl/rocm6.2
.\.venv\Scripts\python.exe -m pip install "transformers>=5.12" accelerate
```
> Torch choices: default index for NVIDIA/CUDA, CPU index for CPU-only, ROCm index for AMD GPU.
### Version and library notes for Qwen3.5/3.6-MoE models ### Version and library notes for Qwen3.5/3.6-MoE models