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/ops/__init__.py

@@ -7,9 +7,7 @@ from astrai.extension.ops.attention import (
     attn_paged_prefill,
     attn_prefill,
 )
-from astrai.extension.ops.gemm import bf16_gemm
 from astrai.extension.ops.rotary import rotary_emb
-from astrai.extension.ops.swiglu import bf16_swiglu
 
 __all__ = [
     "TensorLayout",
@@ -17,7 +15,5 @@ __all__ = [
     "attn_paged_decode",
     "attn_paged_prefill",
     "attn_prefill",
-    "bf16_gemm",
-    "bf16_swiglu",
     "rotary_emb",
 ]