Gaurav Garg 41e3f02647 cuda : revert CUDA_SCALE_LAUNCH_QUEUES override until investigated (#19227) ... Hangs were reported on Jetson Orin AGX if we set CUDA_SCALE_LAUNCH_QUEUES=4x. Reverting the previous PR (#19042) and updating the document to consider setting CUDA_SCALE_LAUNCH_QUEUES=4x for faster throughput on multi-GPU systems.		2026-02-03 08:41:02 +02:00
..
android
backend	Remove support for Nvidia & AMD GPU, because the oneAPI plugin for Nvidia & AMD GPU is unavailable: download/installation channels are out of work. (#19246)	2026-02-02 21:06:21 +08:00
development
multimodal	docs : Minor cleanups (#19252)	2026-02-02 08:38:55 +02:00
ops	sycl: implement GGML_OP_TOP_K (#19242)	2026-02-02 21:05:51 +08:00
android.md
build-riscv64-spacemit.md
build-s390x.md
build.md	cuda : revert CUDA_SCALE_LAUNCH_QUEUES override until investigated (#19227)	2026-02-03 08:41:02 +02:00
docker.md
function-calling.md
install.md
llguidance.md
multimodal.md
ops.md	sycl: implement GGML_OP_TOP_K (#19242)	2026-02-02 21:05:51 +08:00
preset.md
speculative.md