install jit on liunux fedora, TPS in chat

QUICKSTART.md

@@ -244,6 +244,38 @@ HF_HOME=/path/to/models .venv-rocm/bin/meshnet-node start \
   --quantization bfloat16
 ```
 
+### Linux ROCm: Triton JIT compiler prerequisite
+
+Some model/runtime paths invoke Triton at the first real forward. Triton builds a local HIP
+support module before that kernel can run, so a host C compiler must be discoverable on
+`PATH`. A successful PyTorch allocation or Node startup does not prove this prerequisite;
+without it, the first `/forward` can fail with `Failed to find C compiler`.
+
+On Fedora, install Clang once:
+
+```bash
+sudo dnf install -y clang
+```
+
+Restart the Node from a shell where `clang` is on `PATH`. If a custom shell or service does
+not inherit the system path, set the compiler explicitly for that launch:
+
+```bash
+CC=/usr/bin/clang CXX=/usr/bin/clang++ \
+  HF_HOME=/path/to/models .venv-rocm/bin/meshnet-node start \
+  --tracker <tracker-url> --model <selected-model>
+```
+
+`CC`/`CXX` are normally unnecessary after Clang is installed; they are a diagnostic override,
+not a Python dependency. Other Linux distributions should install their system `clang` package
+through the OS package manager.
+
+**Windows NVIDIA/Triton:** use native PowerShell and install `triton-windows`, then install or
+upgrade `flash-linear-attention` when the selected model uses it. `triton-windows` supplies the
+supported Windows compiler path; do not apply Linux `dnf`/`CC` instructions to Windows. If a
+Windows Node still reports a compiler error, capture `python -c "import triton; print(triton.__version__)"`
+and the exact error before installing arbitrary CUDA toolkits or `causal-conv1d`.
+
 **Troubleshooting notes:**
 
 - `torch.version.hip is None` means you installed a CPU/CUDA torch build, not ROCm.
@@ -261,6 +293,9 @@ HF_HOME=/path/to/models .venv-rocm/bin/meshnet-node start \
   your GPU arch. Compare `torch.cuda.get_device_properties(0).gcnArchName`
   against `torch.cuda.get_arch_list()`; if your arch is missing, install a wheel
   built for it (see the Strix Halo/gfx1151 note above).
+- `Failed to find C compiler` during a real forward is a Triton JIT host-toolchain failure.
+  On Fedora install `clang` as shown above, confirm `command -v clang`, and restart the Node;
+  it is separate from ROCm driver and device-access troubleshooting.
 
 ### Qwen3.5/3.6-MoE notes