whisper.cpp/ggml at 414901a42c4ac9998615d45ee4e0f6cfe3064377 - whisper.cpp - Gitea: Git with a cup of tea

public_git/whisper.cpp

mirror of https://github.com/ggml-org/whisper.cpp.git synced 2026-10-05 05:51:22 +02:00

Files

T

History

Jeff Bolz 414901a42c vulkan: Implement topk_moe fused shader, ported from CUDA (llama/16641)

This is similar to the CUDA shader from #16130, but doesn't use shared memory
and handles different subgroup sizes.

2025-10-22 12:58:11 +03:00

..

ggml: Skip backend library linking code when GGML_BACKEND_DL=ON (llama/15094)

2025-08-18 20:30:45 +03:00

rpc : report actual free memory (llama/16616)

2025-10-22 12:58:11 +03:00

vulkan: Implement topk_moe fused shader, ported from CUDA (llama/16641)

2025-10-22 12:58:11 +03:00

.gitignore

…

CMakeLists.txt

ggml webgpu: profiling, CI updates, reworking of command submission (llama/16452)

2025-10-12 11:16:23 +03:00