From: pmysl <redacted>
Date: Sun, 21 Apr 2024 12:49:30 +0000 (+0200)
Subject: gguf-py : add IQ1_M to GGML_QUANT_SIZES (#6761)
X-Git-Tag: upstream/0.0.4488~1781
X-Git-Url: https://git.djapps.eu/?a=commitdiff_plain;h=c1386c936e9fbc38eb2816c711ab28f13355708e;p=pkg%2Fggml%2Fsources%2Fllama.cpp

gguf-py : add IQ1_M to GGML_QUANT_SIZES (#6761)
---

diff --git a/gguf-py/gguf/constants.py b/gguf-py/gguf/constants.py
index ba24065a..06cb26a7 100644
--- a/gguf-py/gguf/constants.py
+++ b/gguf-py/gguf/constants.py
@@ -872,6 +872,7 @@ GGML_QUANT_SIZES = {
     GGMLQuantizationType.I32:     (1, 4),
     GGMLQuantizationType.I64:     (1, 8),
     GGMLQuantizationType.F64:     (1, 8),
+    GGMLQuantizationType.IQ1_M:   (256, QK_K // 8 + QK_K // 16  + QK_K // 32),
 }