whisper.cpp/ggml
Georgi Gerganov cf4bd07028 cuda : enable CUDA graphs for MMID 1 <= BS <= 4 (llama/19645)
* cuda : enable CUDA graphs for MMID BS <= 4

* cont : add stream capture check

Co-authored-by: Oliver Simons <osimons@nvidia.com>

* cont : add MMVQ_MMID_MAX_BATCH_SIZE

---------

Co-authored-by: Oliver Simons <osimons@nvidia.com>
2026-02-27 20:57:58 +02:00
..
cmake cmake : remove unused file (ggml/1419) 2026-02-08 09:29:10 +02:00
include ggml : make `ggml_is_view` as API (llama/19539) 2026-02-27 20:57:58 +02:00
src cuda : enable CUDA graphs for MMID 1 <= BS <= 4 (llama/19645) 2026-02-27 20:57:58 +02:00
.gitignore
CMakeLists.txt ggml : bump version to 0.9.7 (ggml/1425) 2026-02-27 20:57:58 +02:00