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

wip -more responsive UI, better routing

Browse Source
This commit is contained in:
Dobromir Popov
2026-07-08 09:07:54 +02:00
parent 518c259cd3
commit 3d82188dc1
14 changed files with 506 additions and 39 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
docs/INSTALL_WINDOWS.md
View File

@@ -106,14 +106,24 @@ meshnet-node --help
python -c "import transformers; print(transformers.__version__)"
```
`transformers` must be **≥ 5.12** for Qwen3.5/3.6-MoE models (older versions fail
with `'Qwen3_5MoeConfig' object has no attribute 'vocab_size'`). If you install
into an existing conda/miniforge env instead of a fresh venv, run
`pip install -U transformers` there. The startup warning about
`flash-linear-attention` / `causal-conv1d` ("fast path is not available") is
harmless on CPU — those are optional CUDA-only kernels.
---
`transformers` must be **≥ 5.12** for Qwen3.5/3.6-MoE models (older versions fail
with `'Qwen3_5MoeConfig' object has no attribute 'vocab_size'`). If you install
into an existing conda/miniforge env instead of a fresh venv, run
`pip install -U transformers` there. The startup warning about
`flash-linear-attention` / `causal-conv1d` ("fast path is not available") is
harmless on CPU — those are optional CUDA-only kernels.
If you run the node from native Windows instead of WSL2, install the Triton shim
in the same environment:
```powershell
python -m pip install triton-windows
```
Without it, Qwen3.5/3.6-MoE startup can fail with the misleading message
`Could not import module 'Qwen3_5MoeForCausalLM'`.
---
## Step 6 — Pre-download the model shard