refactor: root kernel includes at csrc/kernels

- add the kernels directory to CMake target include paths and drop all ../-relative includes in kernel sources - reference shared primitives as common/*.cuh and the fp8 type header as fp8/common.h - update standalone test nvcc commands in file headers and cuda_kernels.md to -I csrc/kernels
2026-09-01 14:43:38 +08:00
parent 63f23a4454
commit 1c17e80882
15 changed files with 23 additions and 22 deletions
@@ -2,7 +2,7 @@
 // Collective epilogue: fused bias, the bf16 scatter of the fp32 accumulators
 // through the reclaimed operand shared memory, and the coalesced copy-out.

-#include "../common.h"
+#include "fp8/common.h"
 #include "policy.cuh"

 namespace astrai {