refactor: remove bf16 gemm and swiglu kernels and rebuild csrc benchmarks

- delete csrc/kernels/gemm.cu and swiglu.cu and drop their CMake and setup.py registration
- remove the ops wrappers plus backend/linear.py and backend/swiglu.py so Linear and MLP call F.linear directly
- drop the four gemm and swiglu kernel test files and prune the stale cuda_kernels.md sections
- add csrc/bench benchmarks for the remaining kernels: attention decode prefill paged decode paged prefill versus single-launch SDPA references, rotary versus the torch fallback, fp8 quantize and mm_fp8 versus torch baselines
- attention, rotary_emb, and fp8_ops kernels are unchanged

astrai/extension/backend/__init__.py

@@ -11,9 +11,7 @@ from astrai.extension.backend.attention import (
     attn_backend,
     get_backend,
 )
-from astrai.extension.backend.linear import linear
 from astrai.extension.backend.rotary import apply_rotary_emb
-from astrai.extension.backend.swiglu import swiglu
 
 __all__ = [
     "ATTN_BACKEND",
@@ -26,6 +24,4 @@ __all__ = [
     "attention",
     "attn_backend",
     "get_backend",
-    "linear",
-    "swiglu",
 ]