musa: support bf16

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>

ktransformers/ktransformers_ext/cpu_backend/vendors/musa.h

 #pragma once
 
 #include <musa_runtime.h>
+#include <musa_bf16.h>
 
 #define cudaLaunchHostFunc musaLaunchHostFunc
 #define cudaStream_t musaStream_t
-#define cudaHostFn_t musaHostFn_t
\ No newline at end of file
+#define cudaHostFn_t musaHostFn_t
+#define nv_bfloat16 mt_bfloat16
\ No newline at end of file

setup.py

@@ -350,6 +350,7 @@ elif MUSA_HOME is not None:
         "at::cuda": "at::musa",
         "#include <ATen/cuda/CUDAContext.h>": "#include \"torch_musa/csrc/aten/musa/MUSAContext.h\"",
         "#include <c10/cuda/CUDAGuard.h>": "#include \"torch_musa/csrc/core/MUSAGuard.h\"",
+        "nv_bfloat16": "mt_bfloat16",
         }).run()
     ops_module = MUSAExtension('KTransformersOps', [
         'ktransformers/ktransformers_ext/cuda_musa/custom_gguf/dequant.mu',