summaryrefslogtreecommitdiff
path: root/ggml/src/iqk/iqk_quantize.h
diff options
context:
space:
mode:
Diffstat (limited to 'ggml/src/iqk/iqk_quantize.h')
-rw-r--r--ggml/src/iqk/iqk_quantize.h16
1 files changed, 16 insertions, 0 deletions
diff --git a/ggml/src/iqk/iqk_quantize.h b/ggml/src/iqk/iqk_quantize.h
index ad2294c5..fb436e57 100644
--- a/ggml/src/iqk/iqk_quantize.h
+++ b/ggml/src/iqk/iqk_quantize.h
@@ -99,6 +99,22 @@ size_t quantize_iq4_xs_r4(const float * GGML_RESTRICT src, void * GGML_RESTRICT
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_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);
+void dequantize_row_iq2_bn (const block_iq2_bn * GGML_RESTRICT x, float * GGML_RESTRICT y, int64_t k);
+size_t quantize_iq2_bn (const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int64_t nrows, int64_t n_per_row, const float * imatrix);
+void vec_dot_iq2_bn_q8_K64(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_r4_ref (const float * GGML_RESTRICT x, block_iq2_bn * GGML_RESTRICT y, int64_t k);
+void quantize_row_iq2_bn_r4(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k);
+void dequantize_row_iq2_bn_r4(const block_iq2_bn * GGML_RESTRICT x, float * GGML_RESTRICT y, int64_t k);
+size_t quantize_iq2_bn_r4(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int64_t nrows, int64_t n_per_row, const float * imatrix);
+void vec_dot_iq2_bn_r4_q8_K64(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_K64_ref(const float * GGML_RESTRICT x, block_q8_K64 * GGML_RESTRICT y, int64_t k);
+void quantize_row_q8_K64(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k);
+void quantize_row_q8_K16(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k);
+
#ifdef __cplusplus
}
#endif