iq3_k: Basics

Quantize/dequantize, CUDA dequantize.
PPL of LLaMA-3.1-8B is better than iq3_s and iq3_m.

1 files changed, 6 insertions, 0 deletions

diff --git a/ggml/src/iqk/iqk_quantize.h b/ggml/src/iqk/iqk_quantize.h
index b8b03169..0295eb99 100644
--- a/ggml/src/iqk/iqk_quantize.h
+++ b/ggml/src/iqk/iqk_quantize.h
@@ -19,6 +19,12 @@ size_t quantize_iq2_k(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst,
 void   dequantize_row_iq2_k(const block_iq2_k  * GGML_RESTRICT x, float * GGML_RESTRICT y, int64_t k);
 void   vec_dot_iq2_k_q8_k(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
 
+void   quantize_row_iq3_k_ref(const float * GGML_RESTRICT x, block_iq3_k  * GGML_RESTRICT y, int64_t k);
+void   quantize_row_iq3_k(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k);
+size_t quantize_iq3_k(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int64_t nrows, int64_t n_per_row, const float * imatrix);
+void   dequantize_row_iq3_k(const block_iq3_k  * GGML_RESTRICT x, float * GGML_RESTRICT y, int64_t k);
+void   vec_dot_iq3_k_q8_k(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
+
 void   quantize_row_iq4_k_ref(const float * GGML_RESTRICT x, block_iq4_k  * GGML_RESTRICT y, int64_t k);
 void   quantize_row_iq4_k(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k);
 size_t quantize_iq4_k(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int64_t nrows, int64_t n_per_row, const float * imatrix);