ggml : add Q5_0 and Q5_1 quantization (#1187)

* ggml : add Q5_0 quantization (cuBLAS only)

* ggml : fix Q5_0 qh -> uint32_t

* ggml : fix q5_0 histogram stats

* ggml : q5_0 scalar dot product

* ggml : q5_0 ARM NEON dot

* ggml : q5_0 more efficient ARM NEON using uint64_t masks

* ggml : rename Q5_0 -> Q5_1

* ggml : adding Q5_0 mode

* quantize : add Q5_0 and Q5_1 to map

* ggml : AVX2 optimizations for Q5_0, Q5_1 (#1195)

---------

Co-authored-by: Stephan Walter <stephan@walter.name>

1 files changed, 6 insertions, 2 deletions

diff --git a/ggml.h b/ggml.h
index 8300a0c..d9d3d21 100644
--- a/ggml.h
+++ b/ggml.h
@@ -222,8 +222,10 @@ extern "C" {
         GGML_TYPE_Q4_1 = 3,
         GGML_TYPE_Q4_2 = 4,
         GGML_TYPE_Q4_3 = 5,
-        GGML_TYPE_Q8_0 = 6,
-        GGML_TYPE_Q8_1 = 7,
+        GGML_TYPE_Q5_0 = 6,
+        GGML_TYPE_Q5_1 = 7,
+        GGML_TYPE_Q8_0 = 8,
+        GGML_TYPE_Q8_1 = 9,
         GGML_TYPE_I8,
         GGML_TYPE_I16,
         GGML_TYPE_I32,
@@ -833,6 +835,8 @@ extern "C" {
     GGML_API size_t ggml_quantize_q4_1(const float * src, void * dst, int n, int k, int64_t * hist);
     GGML_API size_t ggml_quantize_q4_2(const float * src, void * dst, int n, int k, int64_t * hist);
     GGML_API size_t ggml_quantize_q4_3(const float * src, void * dst, int n, int k, int64_t * hist);
+    GGML_API size_t ggml_quantize_q5_0(const float * src, void * dst, int n, int k, int64_t * hist);
+    GGML_API size_t ggml_quantize_q5_1(const float * src, void * dst, int n, int k, int64_t * hist);
     GGML_API size_t ggml_quantize_q8_0(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);