Fix CPU Hub kernel backend selection

[SiluPanda]

Description

The fused CPU 4-bit GEMM loader knows it is registering a CPU kernel, but it let kernels infer the backend from the installed PyTorch build. With a CUDA PyTorch wheel, that selects CUDA even though kernels-community/quantization-bitsandbytes publishes a CPU build, so the fused kernel is rejected and bitsandbytes falls back after logging a warning.

Pass backend="cpu" explicitly when loading the Hub kernel. The existing best-effort warning and fallback behavior remains unchanged.

Tests

• Added regression coverage that asserts the loader requests version=1 and backend="cpu".
• Added coverage for the existing warning-and-fallback path.
• PYTHONPATH=. .venv/bin/pytest tests/test_cpu_ops.py -v --tb=short (2 passed)
• .venv/bin/pre-commit run --all-files (all hooks passed)

Fixes #2064

AI assistance: This change was implemented with OpenAI Codex and independently reviewed and validated before submission.