llama.cpp/ggml/src/ggml-metal at 58d07a8043a1395177cf77b3e4f388e34182ae64 - llama.cpp - Gitea: Git with a cup of tea

Lumpiasty/llama.cpp

Files

T

History

Gian-Carlo PascuttoandGeorgi Gerganov 58d07a8043 metal : copy kernels for quant to F32/F16 conversions (#12017 )

metal: use dequantize_q templates

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

2025-02-25 11:27:58 +02:00

..

CMakeLists.txt

ggml : do not install metal source when embed library (ggml/1054)

2025-01-04 16:09:53 +02:00

ggml-metal-impl.h

ggml: add GGML_SET Metal kernel + i32 CPU kernel (ggml/1037)

2024-12-05 13:27:33 +02:00

ggml-metal.m

metal : copy kernels for quant to F32/F16 conversions (#12017 )

2025-02-25 11:27:58 +02:00

ggml-metal.metal

metal : copy kernels for quant to F32/F16 conversions (#12017 )

2025-02-25 11:27:58 +02:00