2-bit quantizations (#4897)

* imatrix: load

* imatrix: WIP

* imatrix: Add Q2_K quantization

* imatrix: also guard against Q2_K_S quantization without importance matrix

* imatrix: guard even more against low-bit quantization misuse

---------

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

1 files changed, 6 insertions, 3 deletions

diff --git a/ggml.h b/ggml.h
index b18ba781..1187074f 100644
--- a/ggml.h
+++ b/ggml.h
@@ -2067,10 +2067,13 @@ extern "C" {
     GGML_API size_t ggml_quantize_q4_K(const float * src, void * dst, int n, int k, int64_t * hist);
     GGML_API size_t ggml_quantize_q5_K(const float * src, void * dst, int n, int k, int64_t * hist);
     GGML_API size_t ggml_quantize_q6_K(const float * src, void * dst, int n, int k, int64_t * hist);
-    GGML_API size_t ggml_quantize_iq2_xxs(const float * src, void * dst, int n, int k, int64_t * hist);
-    GGML_API size_t ggml_quantize_iq2_xs (const float * src, void * dst, int n, int k, int64_t * hist);
 
-    GGML_API size_t ggml_quantize_chunk(enum ggml_type type, const float * src, void * dst, int start, int n, int64_t * hist);
+    GGML_API size_t ggml_quantize_chunk(enum ggml_type type, const float * src, void * dst,
+            int start, int nrows, int n_per_row, int64_t * hist, const float * imatrix);
+
+    // These are needed for IQ2_XS and IQ2_XXS quantizations
+    GGML_API void ggml_init_iq2_quantization(enum ggml_type type);
+    GGML_API void ggml_deinit_iq2_quantization(enum ggml_type type);
 
     //
     // Importance matrix