Add support for I8, I16 and I32

These types are allowed in the GGUF specification.
ggerganov · Mar 13, 2024 · 2d85ba2 · 2d85ba2
1 parent b7e9d5c
commit 2d85ba2
Showing 1 changed file with 7 additions and 0 deletions.
diff --git a/gguf-py/gguf/constants.py b/gguf-py/gguf/constants.py
@@ -661,6 +661,10 @@ class GGMLQuantizationType(IntEnum):
     IQ3_S   = 21
     IQ2_S   = 22
     IQ4_XS  = 23
+    I8      = 24
+    I16     = 25
+    I32     = 26
+
 
 
 class GGUFEndian(IntEnum):
@@ -727,6 +731,9 @@ def get_type(val: Any) -> GGUFValueType:
     GGMLQuantizationType.IQ3_S:   (256, 2 + QK_K // 4 + QK_K // 8 + QK_K // 32 + 4),
     GGMLQuantizationType.IQ2_S:   (256, 2 + QK_K // 4 + QK_K // 16),
     GGMLQuantizationType.IQ4_XS:  (256, 2 + 2 + QK_K // 2 + QK_K // 64),
+    GGMLQuantizationType.I8:      (1, 1),
+    GGMLQuantizationType.I16:     (1, 2),
+    GGMLQuantizationType.I32:     (1, 4),
 }