llama.cpp/ggml at f0198ef6fcb024c8cddc6e593bf16b4006dffda4 - llama.cpp - Gitea: Git with a cup of tea

sdgoij/llama.cpp

mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-05-13 04:24:17 +00:00

Files

History

Gaurav Garg aa8b62105c Support device-specific host buffer types if all underlying backends expose the same type. This allows using pinned memory instead of pageable memory for CUDA.

Fix compilation errors.

2026-02-16 15:39:26 +05:30

..

Remove shfl and AllReduce from backend interface

2026-02-11 14:51:37 +01:00

support for tensor dims % n_devs != 0

2026-02-13 00:40:00 +01:00

Support device-specific host buffer types if all underlying backends expose the same type. This allows using pinned memory instead of pageable memory for CUDA.

2026-02-16 15:39:26 +05:30

.gitignore

vulkan : cmake integration (#8119 )

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

CMakeLists.txt

GGML: HIP: add RCCL support

2026-02-11 14:51:33 +01:00