Q5_K_R4 (#132)

* q5_k_r4: WIP

* q5_k_r4: Zen4 and AVX2

We get PP-512(LLaMA-3.1-8B) = 248.3 t/s on Zen4.
Q5_K_S has PP-512 = 190 t/s.

* q5_k_r4: NEON

We get PP-512(LLaMA-3.1-8B) = 96.1 t/s.

---------

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 8819620d..77c34fea 100644
--- a/ggml/src/iqk/iqk_quantize.h
+++ b/ggml/src/iqk/iqk_quantize.h
@@ -115,6 +115,12 @@ size_t quantize_q4_k_r4(const float * GGML_RESTRICT src, void * GGML_RESTRICT ds
 void   dequantize_row_q4_k_r4(const block_q4_k_r4  * GGML_RESTRICT x, float * GGML_RESTRICT y, int64_t k);
 void   vec_dot_q4_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_q5_k_r4_ref(const float * GGML_RESTRICT x, block_q5_k_r4  * GGML_RESTRICT y, int64_t k);
+void   quantize_row_q5_k_r4(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k);
+size_t quantize_q5_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_q5_k_r4(const block_q5_k_r4  * GGML_RESTRICT x, float * GGML_RESTRICT y, int64_t k);
+void   vec_dot_q5_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_q6_k_r4_ref(const float * GGML_RESTRICT x, block_q6_k_r4  * GGML_RESTRICT y, int64_t k);
 void   quantize_row_q6_k_r4(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k);
 size_t quantize_q6_k_r4(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int64_t nrows, int64_t n_per_row, const float * imatrix);