This commit is contained in:
Dobromir Popov
2026-06-30 18:31:22 +03:00
2 changed files with 27 additions and 10 deletions

View File

@@ -71,7 +71,7 @@ reachable node on the LAN.
# Example repo path; adjust to wherever you cloned it
cd D:\DEV\workspace\REPOS\git.d-popov.com\neuron-tai
py -3 -m venv .venv
python -m venv .venv
.\.venv\Scripts\python.exe -m pip install --upgrade pip setuptools wheel
.\.venv\Scripts\pip.exe install -e packages\tracker -e packages\node -e packages\p2p -e packages\gateway -e packages\relay
@@ -82,6 +82,12 @@ py -3 -m venv .venv
.\.venv\Scripts\meshnet-node.exe --help
```
For `start`-specific flags, run:
```powershell
.\.venv\Scripts\meshnet-node.exe start --help
```
3. Find the Windows LAN IP address:
```powershell
@@ -112,7 +118,7 @@ $env:HF_HOME = "D:\DEV\models"
.\.venv\Scripts\meshnet-node.exe start `
--tracker http://192.168.0.179:8081 `
--model-id Qwen/Qwen2.5-0.5B-Instruct `
--model Qwen/Qwen2.5-0.5B-Instruct `
--shard-start 12 --shard-end 23 `
--quantization bfloat16 `
--host 0.0.0.0 `
@@ -120,9 +126,13 @@ $env:HF_HOME = "D:\DEV\models"
--port 8005
```
The example above starts the Windows node as the second half of a split Qwen
model. To run the full model on Windows instead, omit `--shard-start` and
`--shard-end`.
One-line variants:
```powershell
// only this works - when not behind NAT(wsl), and via IP. Revisit when relaying/RPC is implemented
.\.venv\Scripts\meshnet-node.exe start --tracker http://192.168.0.179:8081 --model Qwen/Qwen2.5-0.5B-Instruct --advertise-host 192.168.0.20
.\.venv\Scripts\meshnet-node.exe start --tracker http://ai.neuron.d-popov.com --model Qwen/Qwen2.5-0.5B-Instruct --advertise-host 192.168.0.20
```
`--host 0.0.0.0` binds the node to all Windows interfaces. `--advertise-host`
is what the tracker gives to other nodes, so it must be the Windows LAN IP that
@@ -173,7 +183,7 @@ Then a node only needs the public tracker address:
```bash
.venv/bin/meshnet-node start \
--tracker https://ai.neuron.d-popov.com \
--model-id Qwen/Qwen2.5-0.5B-Instruct
--model Qwen/Qwen2.5-0.5B-Instruct
```
---
@@ -207,7 +217,7 @@ Keep this terminal open.
cd /run/media/popov/d/DEV/repos/d-popov.com/AI
HF_HOME=/run/media/popov/d/DEV/models \
.venv/bin/meshnet-node start \
--model-id Qwen/Qwen2.5-0.5B-Instruct \
--model Qwen/Qwen2.5-0.5B-Instruct \
--quantization bfloat16 \
--tracker http://localhost:8080 \
--port 8001
@@ -276,7 +286,7 @@ Split Qwen2.5-0.5B's 24 layers across two node processes to test the sharded pip
```bash
HF_HOME=/run/media/popov/d/DEV/models \
.venv/bin/meshnet-node start \
--model-id Qwen/Qwen2.5-0.5B-Instruct \
--model Qwen/Qwen2.5-0.5B-Instruct \
--shard-start 0 --shard-end 11 \
--quantization bfloat16 \
--tracker http://localhost:8080 \
@@ -287,7 +297,7 @@ HF_HOME=/run/media/popov/d/DEV/models \
```bash
HF_HOME=/run/media/popov/d/DEV/models \
.venv/bin/meshnet-node start \
--model-id Qwen/Qwen2.5-0.5B-Instruct \
--model Qwen/Qwen2.5-0.5B-Instruct \
--shard-start 12 --shard-end 23 \
--quantization bfloat16 \
--tracker http://localhost:8080 \