refactor: template AttentionParams, rename .cuh to .h

- Convert AttentionParams to a template struct supporting arbitrary types
- Rename attn_common.cuh -> attn_common.h (no CUDA-specific code remains)
- Include standard headers explicitly in each .cuh instead of via attn_common.cuh
- Allow .h files in csrc/ via .gitignore

csrc/kernels/attn_prefill_split_q.cuh

@@ -1,5 +1,9 @@
 #pragma once
-#include "attn_common.cuh"
+#include <cfloat>
+#include <cuda_bf16.h>
+#include "attn_common.h"
+
+using bf16 = __nv_bfloat16;
 
 // v9: group-split register blocking. G threads cooperate on one query row,
 // each owning HEAD_DIM/G dims of qreg[]/acc[]. Small per-thread footprint keeps
@@ -31,7 +35,7 @@ __device__ __forceinline__ void ld8(const bf16* p, float* o) {
 }
 
 template <int HEAD_DIM, int G, int ROWS, int P_BC>
-__global__ void attn_prefill_split_q_kernel_t(AttentionParams p) {
+__global__ void attn_prefill_split_q_kernel_t(AttentionParams<bf16> p) {
     constexpr int DPT = HEAD_DIM / G;
 
     int q_tile = blockIdx.x;