IQ3_K_R4 (#145)

* iq3_k_r4 WIP

* iq3_k_r4: Zen4

* iq3_k_r4: AVX2

* iq3_k_r4: NEON

* iq3_k_r4: faster matrix x vector multiplication on NEON

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>

1 files changed, 6 insertions, 0 deletions

diff --git a/ggml/src/iqk/iqk_quantize.h b/ggml/src/iqk/iqk_quantize.h
index e8721a5e..1ca66bd8 100644
--- a/ggml/src/iqk/iqk_quantize.h
+++ b/ggml/src/iqk/iqk_quantize.h
@@ -145,6 +145,12 @@ size_t quantize_iq4_k_r4(const float * GGML_RESTRICT src, void * GGML_RESTRICT d
 void   dequantize_row_iq4_k_r4(const block_iq4_k_r4  * GGML_RESTRICT x, float * GGML_RESTRICT y, int64_t k);
 void   vec_dot_iq4_k_r4_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_r4_ref(const float * GGML_RESTRICT x, block_iq3_k_r4  * GGML_RESTRICT y, int64_t k);
+void   quantize_row_iq3_k_r4(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k);
+size_t quantize_iq3_k_r4(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_r4(const block_iq3_k_r4  * GGML_RESTRICT x, float * GGML_RESTRICT y, int64_t k);
+void   vec_dot_iq3_k_r4_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_q8_k_r8_ref(const float * GGML_RESTRICT x, block_q8_k_r8  * GGML_RESTRICT y, int64_t k);
 void   quantize_row_q8_k_r8(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k);
 size_t quantize_q8_k_r8(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int64_t nrows, int64_t n_per_row, const float * imatrix);