happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Update OPENVINO.md

This commit is contained in:
Yamini Nimmagadda 2026-01-12 17:37:26 -08:00 committed by Mustafa Cavus
parent 9ba324726a
commit 61552e4450
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docs/backend/OPENVINO.md
View File

@ -52,7 +52,7 @@ Accuracy and performance optimizations for quantized models are still work in pr
- **Primary supported quantization scheme is `Q4_0`**
- `Q4_0` and `Q4_1` tensors are requantized to int4 gs128 symmetric
- `Q6_K` tensors are requentized to int8 except for the token embedding matrix
- `Q6_K` tensors are requentized to int8 except for the token embedding matrix which is dequantized to fp16
#### Additional Notes