wip -more responsive UI, better routing

QUICKSTART.md

@@ -38,12 +38,30 @@ python3 -m venv .venv
   `python -c "import transformers; print(transformers.__version__)"` and upgrade
   with `pip install -U transformers` in the environment that runs `meshnet-node`
   (conda/miniforge users: upgrade inside that env, not a layered `.venv`).
-- The startup warning
-  `The fast path is not available because one of the required library is not installed`
-  is **harmless** — transformers falls back to a pure-torch implementation of the
-  linear-attention layers. The fast-path packages (`flash-linear-attention`,
-  `causal-conv1d`) are CUDA-only kernels: install them for GPU speed if you want,
-  skip them entirely on CPU nodes.
+- **Linear-attention fast path (GPU only).** Qwen3.5/3.6 use hybrid linear-attention
+  layers; without optional CUDA kernels, Transformers falls back to slower pure-PyTorch
+  code and prints `The fast path is not available…` at startup. That warning is
+  harmless — inference still works. On native Windows, install `triton-windows` in
+  the same env as `meshnet-node`; otherwise `flash-linear-attention` can fail during
+  import with `Could not import module 'Qwen3_5MoeForCausalLM'`. Install the
+  acceleration packages into the same env as `meshnet-node` for GPU speed; skip on
+  CPU-only nodes:
+
+  ```bash
+  # Native Windows
+  pip install triton-windows
+
+  # NVIDIA (CUDA)
+  pip install flash-linear-attention[cuda] causal-conv1d
+
+  # AMD (ROCm) — match your torch index, then:
+  pip install flash-linear-attention[rocm] causal-conv1d
+  ```
+
+  Restart the node after install; the warning should disappear. Expect the largest
+  gain on GPU nodes serving linear-attention layers (roughly three quarters of
+  Qwen3.6 layers); end-to-end chat speed still depends on the slowest hop in a
+  split route.
 - `pip install nvidia-ml-py` silences the pynvml deprecation warning on NVIDIA hosts.
 
 ## Bootstrap a tracker on a new machine