IQ1_M_R4: better 1.75 bpw quants (#187)

* iq1_m_r4: basics (quantize/dequantize)

* iq1_m_r4: Zen4 gemm

* iq1_m_r4: neon gemm

* iq1_m_r4: switch to q8_0_x4 also on AVX2/Zen4

With the deltas being per group of 8, we cannot make use
of the q8 sums stored in q8_1, so we get a tiny gain by
using q8_0_x4.

* iq1_m_r4: rename mul_mat_iq1_m_r4_q8_1 to mul_mat_iq1_m_r4_q8_0

---------

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 9a3c5dc6..0dbb88bd 100644
--- a/ggml/src/iqk/iqk_quantize.h
+++ b/ggml/src/iqk/iqk_quantize.h
@@ -205,6 +205,12 @@ size_t quantize_iq1_s_r4(const float * GGML_RESTRICT src, void * GGML_RESTRICT d
 void   dequantize_row_iq1_s_r4(const block_iq1_s_r4  * GGML_RESTRICT x, float * GGML_RESTRICT y, int64_t k);
 void   vec_dot_iq1_s_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_iq1_m_r4_ref(const float * GGML_RESTRICT x, block_iq1_m_r4  * GGML_RESTRICT y, int64_t k);
+void   quantize_row_iq1_m_r4(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k);
+size_t quantize_iq1_m_r4(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int64_t nrows, int64_t n_per_row, const float * imatrix);
+void   dequantize_row_iq1_m_r4(const block_iq1_m_r4  * GGML_RESTRICT x, float * GGML_RESTRICT y, int64_t k);
+void   vec_dot_iq1_m_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);