whisper.cpp/ggml at f1fdb91e95f9941fedbdb718dfa2e233716639b0 - whisper.cpp - Gitea: Git with a cup of tea

public_git/whisper.cpp

mirror of https://github.com/ggml-org/whisper.cpp.git synced 2026-10-04 13:31:18 +02:00

Files

T

History

Max Krasnyansky f1fdb91e95 cpu: introduce chunking for flash attention (llama/16829)

Factor out the core FA loop into flash_atten_f16_one_chunk and add an outter loop
on top that handles the chunks.

2025-11-09 23:38:03 +02:00

..

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

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

Add experimental ggml-hexagon backend for the Hexagon NPU (llama/16547)

2025-11-09 23:38:03 +02:00

cpu: introduce chunking for flash attention (llama/16829)

2025-11-09 23:38:03 +02:00

.gitignore

…

CMakeLists.txt

Add experimental ggml-hexagon backend for the Hexagon NPU (llama/16547)

2025-11-09 23:38:03 +02:00