diff options
Diffstat (limited to 'ggml.h')
-rw-r--r-- | ggml.h | 7 |
1 files changed, 7 insertions, 0 deletions
@@ -1930,12 +1930,19 @@ extern "C" { // quantization // + // TODO: these would probably get removed in favor of the more general ggml_quantize_chunk GGML_API size_t ggml_quantize_q4_0(const float * src, void * dst, int n, int k, int64_t * hist); GGML_API size_t ggml_quantize_q4_1(const float * src, void * dst, int n, int k, int64_t * hist); GGML_API size_t ggml_quantize_q5_0(const float * src, void * dst, int n, int k, int64_t * hist); GGML_API size_t ggml_quantize_q5_1(const float * src, void * dst, int n, int k, int64_t * hist); GGML_API size_t ggml_quantize_q8_0(const float * src, void * dst, int n, int k, int64_t * hist); + GGML_API size_t ggml_quantize_q2_K(const float * src, void * dst, int n, int k, int64_t * hist); + GGML_API size_t ggml_quantize_q3_K(const float * src, void * dst, int n, int k, int64_t * hist); + GGML_API size_t ggml_quantize_q4_K(const float * src, void * dst, int n, int k, int64_t * hist); + GGML_API size_t ggml_quantize_q5_K(const float * src, void * dst, int n, int k, int64_t * hist); + GGML_API size_t ggml_quantize_q6_K(const float * src, void * dst, int n, int k, int64_t * hist); + GGML_API size_t ggml_quantize_chunk(enum ggml_type type, const float * src, void * dst, int start, int n, int64_t * hist); // |