llama.cpp/ggml/src/ggml-vulkan at fe235f434368dfbdf3091a6cea92c00a98d2cee4 - llama.cpp - Gitea: Git with a cup of coffee

Public/llama.cpp

mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-04 12:01:13 +02:00

Files

T

History

Ruben Ortlam 5e6a37cb11 vulkan: warptiles currently assume warp sizes <= 64, clamp to work around larger warps (#27726 )

2026-08-26 19:02:06 +03:00

..

cmake: fix ggml-shaders-gen compiler paths containing spaces (#12747 )

2025-04-04 10:12:40 -03:00

Implemented vulkan cross_entropy_loss and cross_entropy_loss_back (#27216 )

2026-08-26 16:49:32 +02:00

CMakeLists.txt

vulkan : add source groups for shaders (#26666 )

2026-08-20 09:52:28 +03:00

ggml-vulkan.cpp

vulkan: warptiles currently assume warp sizes <= 64, clamp to work around larger warps (#27726 )

2026-08-26 19:02:06 +03:00