clean code

Author: xiaolil1

csrc/pythonInterface.cpp

@@ -384,7 +384,7 @@ void gemm_4bit_inference_bf16(
     int m, int n, int k, int l, sycl::ext::oneapi::bfloat16 * A,  unsigned char* B,   float *absmax, float *datatype, float * out,
     int lda, int ldb, int ldc, int blocksize, sycl::queue* stream
 ) {
-    gemm_4bit_inference_cutlass_dequant<sycl::ext::oneapi::bfloat16, 16>(m, n, k, l, A, B, absmax,  datatype, out, lda, ldb, ldc, blocksize, stream);
+    gemm_4bit_cutlass<sycl::ext::oneapi::bfloat16, 16>(m, n, k, l, A, B, absmax,  datatype, out, lda, ldb, ldc, blocksize, stream);
 }
 #endif
 

csrc/xpu_cutlass.h

@@ -108,7 +108,7 @@ void gemv_4bit_inference_cutlass_cute(int m, int n, int k, T *A, T *B,
                          int ldb, int ldc, int blocksize, sycl::queue *stream);
 
 template <typename T, int BITS>
-void gemm_4bit_inference_cutlass_dequant(int m, int n, int k, int l, T *A, unsigned char *B,
+void gemm_4bit_cutlass(int m, int n, int k, int l, T *A, unsigned char *B,
                          float *absmax, float *datatype, float *out, int lda,
                          int ldb, int ldc, int blocksize, sycl::queue *stream);