The schedule handed to step-aware code (SLA, H3's head bank) was a CPU copy while the call's sigma sits on the GPU, which fails with "Expected all tensors to be on the same device". It now matches the schedule the sampler was given. Test uses the meta device as a stand-in for CUDA.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0164nckPWA2L2ugVqiDcXzc3