Rename q4_0_r4, q8_0_r4 and iq4_xs_r4 to _r8 (#189)

* Rename q4_0_r4 to q4_0_r8 to reflect actual row interleaving

* Rename q8_0_r4 to q8_0_r8 to reflect actual row interleaving

* Rename iq4_xs_r4 to iq4_xs_r8 to reflect actual row interleaving

---------

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

1 files changed, 16 insertions, 16 deletions

diff --git a/ggml/src/iqk/iqk_quantize.h b/ggml/src/iqk/iqk_quantize.h
index 0dbb88bd..ff553ae7 100644
--- a/ggml/src/iqk/iqk_quantize.h
+++ b/ggml/src/iqk/iqk_quantize.h
@@ -67,17 +67,17 @@ size_t quantize_iq4_nl_r4(const float * GGML_RESTRICT src, void * GGML_RESTRICT
 void   dequantize_row_iq4_nl_r4(const block_iq4_nl_r4  * GGML_RESTRICT x, float * GGML_RESTRICT y, int64_t k);
 void   vec_dot_iq4_nl_r4_q8_0(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_q4_0_r4_ref(const float * GGML_RESTRICT x, block_iq4_nl_r8  * GGML_RESTRICT y, int64_t k);
-void   quantize_row_q4_0_r4(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k);
-size_t quantize_q4_0_r4(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int64_t nrows, int64_t n_per_row, const float * imatrix);
-void   dequantize_row_q4_0_r4(const block_iq4_nl_r8  * GGML_RESTRICT x, float * GGML_RESTRICT y, int64_t k);
-void   vec_dot_q4_0_r4_q8_0(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_0_r4_ref(const float * GGML_RESTRICT x, block_q8_0_r8  * GGML_RESTRICT y, int64_t k);
-void   quantize_row_q8_0_r4(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k);
-size_t quantize_q8_0_r4(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int64_t nrows, int64_t n_per_row, const float * imatrix);
-void   dequantize_row_q8_0_r4(const block_q8_0_r8  * GGML_RESTRICT x, float * GGML_RESTRICT y, int64_t k);
-void   vec_dot_q8_0_r4_q8_0(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_q4_0_r8_ref(const float * GGML_RESTRICT x, block_iq4_nl_r8  * GGML_RESTRICT y, int64_t k);
+void   quantize_row_q4_0_r8(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k);
+size_t quantize_q4_0_r8(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int64_t nrows, int64_t n_per_row, const float * imatrix);
+void   dequantize_row_q4_0_r8(const block_iq4_nl_r8  * GGML_RESTRICT x, float * GGML_RESTRICT y, int64_t k);
+void   vec_dot_q4_0_r8_q8_0(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_0_r8_ref(const float * GGML_RESTRICT x, block_q8_0_r8  * GGML_RESTRICT y, int64_t k);
+void   quantize_row_q8_0_r8(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k);
+size_t quantize_q8_0_r8(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int64_t nrows, int64_t n_per_row, const float * imatrix);
+void   dequantize_row_q8_0_r8(const block_q8_0_r8  * GGML_RESTRICT x, float * GGML_RESTRICT y, int64_t k);
+void   vec_dot_q8_0_r8_q8_0(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_0_r4_ref(const float * GGML_RESTRICT x, block_q5_0_r4  * GGML_RESTRICT y, int64_t k);
 void   quantize_row_q5_0_r4(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k);
@@ -91,11 +91,11 @@ size_t quantize_q6_0_r4(const float * GGML_RESTRICT src, void * GGML_RESTRICT ds
 void   dequantize_row_q6_0_r4(const block_q6_0_r4  * GGML_RESTRICT x, float * GGML_RESTRICT y, int64_t k);
 void   vec_dot_q6_0_r4_q8_0(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_xs_r4_ref(const float * GGML_RESTRICT x, block_iq4_xs_r4 * GGML_RESTRICT y, int64_t k);
-void   quantize_row_iq4_xs_r4(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k);
-size_t quantize_iq4_xs_r4(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int64_t nrows, int64_t n_per_row, const float * imatrix);
-void   dequantize_row_iq4_xs_r4(const block_iq4_xs_r4 * GGML_RESTRICT x, float * GGML_RESTRICT y, int64_t k);
-void   vec_dot_iq4_xs_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_iq4_xs_r8_ref(const float * GGML_RESTRICT x, block_iq4_xs_r8 * GGML_RESTRICT y, int64_t k);
+void   quantize_row_iq4_xs_r8(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k);
+size_t quantize_iq4_xs_r8(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int64_t nrows, int64_t n_per_row, const float * imatrix);
+void   dequantize_row_iq4_xs_r8(const block_iq4_xs_r8 * GGML_RESTRICT x, float * GGML_RESTRICT y, int64_t k);
+void   vec_dot_iq4_xs_r8_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_iq2_bn_ref (const float * GGML_RESTRICT x, block_iq2_bn  * GGML_RESTRICT y, int64_t k);
 void   quantize_row_iq2_bn (const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k);