ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-03-11 14:30:02 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
8c0a10e64dbf60fd9946c0cd5e6f59690800b123
ik_llama.cpp/llama.cpp
Kerfuffle 4f0154b0ba llama : support requantizing models instead of only allowing quantization from 16/32bit (#1691) 
* Add support for quantizing already quantized models

* Threaded dequantizing and f16 to f32 conversion

* Clean up thread blocks with spares calculation a bit

* Use std::runtime_error exceptions.
2023-06-10 10:59:17 +03:00

116 KiB
Raw Blame History

View Raw
Reference in New Issue View Git Blame Copy Permalink