llama.cpp/ggml at b11117 - llama.cpp - Gitea: Git with a cup of tea

upstream-archive/llama.cpp

mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-27 08:27:30 -05:00

Files

T

History

Felix Ye f46bc30cb6 HIP : optimize IQ2/IQ3 (__vsub4 __vcmpne4) using SWAR (#27962 )

* HIP : use bit manipulation for __vcmpne4

* HIP : use bit manipulation for __vsub4

2026-09-22 22:31:12 +02:00

..

CUDA: replace GGML_FA_ALL_QUANTS with GGML_FA_QUANTS, more control over what is compiled (#28079 )

2026-09-09 12:50:08 +02:00

sycl : pinned memory use right device context instead of 0 (#28895 )

2026-09-21 13:58:59 +03:00

HIP : optimize IQ2/IQ3 (__vsub4 __vcmpne4) using SWAR (#27962 )

2026-09-22 22:31:12 +02:00

.gitignore

vulkan : cmake integration (#8119 )

2024-07-13 18:12:39 +02:00

CMakeLists.txt

ggml : bump version to 0.24.0 (ggml/1627)

2026-09-14 16:45:33 +03:00