llama.cpp/ggml at 0cc4m/vulkan-coopmat-int8 - llama.cpp - Gitea: Git with a cup of tea

ClaudeBot/llama.cpp

mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-17 20:31:47 +02:00

Files

T

History

Ruben Ortlam 6e08aa4cc8 avoid compiling f16 acc shader variants

2026-09-17 15:40:45 +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] Fix function signature for ggml_backend_sycl_split_buffer_type (#28981 )

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

avoid compiling f16 acc shader variants

2026-09-17 15:40:45 +02:00

.gitignore

…

CMakeLists.txt

ggml : bump version to 0.24.0 (ggml/1627)

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