diff --git a/ggml/src/ggml-impl.h b/ggml/src/ggml-impl.h index 59bae840f..8d9bdc74c 100644 --- a/ggml/src/ggml-impl.h +++ b/ggml/src/ggml-impl.h @@ -390,6 +390,9 @@ static inline ggml_fp16_t ggml_compute_fp32_to_fp16(float f) { #define GGML_COMPUTE_FP16_TO_FP32(x) ggml_compute_fp16_to_fp32(x) #define GGML_COMPUTE_FP32_TO_FP16(x) ggml_compute_fp32_to_fp16(x) +#define GGML_FP16_TO_FP32(x) GGML_COMPUTE_FP16_TO_FP32(x) +#define GGML_FP32_TO_FP16(x) GGML_COMPUTE_FP32_TO_FP16(x) + // precomputed f32 table for f16 (256 KB) // defined in ggml.c, initialized in ggml_init() GGML_API float ggml_table_f32_f16[1 << 16]; diff --git a/ggml/src/ggml-quants.c b/ggml/src/ggml-quants.c index 5bd027159..e389a46db 100644 --- a/ggml/src/ggml-quants.c +++ b/ggml/src/ggml-quants.c @@ -4,7 +4,6 @@ #include "ggml-quants.h" #include "ggml-impl.h" #include "ggml-cpu/ggml-cpu-impl.h" -#include "ggml-cpu/simd-mappings.h" #include "ggml-cpu.h" #include