llama.cpp/ggml at 26394b4e6749a41c3633db040e0987500a5f7013 - llama.cpp - Gitea: Git with a cup of tea

upstream-archive/llama.cpp

mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-21 13:37:29 -05:00

Files

T

History

Anant Shrivastava 1aa2954bde sycl : coalesce MKL-FA softmax loads instead of one work-item per row (#28918 )

* sycl : coalesce MKL-FA softmax loads instead of one work-item per row

* better human readable variable name

2026-09-21 11:07:04 +03:00

..

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] Fix function signature for ggml_backend_sycl_split_buffer_type (#28981 )

2026-09-16 22:15:47 -04:00

sycl : coalesce MKL-FA softmax loads instead of one work-item per row (#28918 )

2026-09-21 11:07:04 +03:00

.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