Wagner Bruna 592d12d0a3 sd: support for CLIP and VAE on different devices (#2184) ... * sd: generalize internal interfaces to place generation on CPU * sd: backend support for multi-device selection * sd: frontend support for multi-device selection * add deprecated flags to avoid breaking old cli args --------- Co-authored-by: Concedo <39025047+LostRuins@users.noreply.github.com>		2026-05-19 21:51:23 +08:00
..
acestep	try fix recent segfault on SIGINT https://github.com/LostRuins/koboldcpp/issues/2215	2026-05-18 22:37:14 +08:00
qwen3tts	use original precision for q3tts	2026-04-30 17:28:11 +08:00
sdcpp	sd: support for CLIP and VAE on different devices (#2184)	2026-05-19 21:51:23 +08:00
tools
ttscpp	hack to allow kokoro to remain functional even with much higher GGML_SCHED_MAX_SPLIT_INPUTS	2026-04-19 20:40:07 +08:00
whispercpp	refactor: handle GGML_VK_VISIBLE_DEVICES at the Python level (#2179)	2026-05-02 23:10:29 +08:00
embeddings_adapter.cpp	refactor: handle GGML_VK_VISIBLE_DEVICES at the Python level (#2179)	2026-05-02 23:10:29 +08:00
ggml_v1.c
ggml_v1.h
ggml_v2-cuda-legacy.cu
ggml_v2-cuda-legacy.h
ggml_v2-cuda.cu
ggml_v2-cuda.h
ggml_v2.c
ggml_v2.h
ggml_v3-cuda.cu
ggml_v3-cuda.h
ggml_v3.c
ggml_v3.h
gpt2_v1.cpp
gpt2_v2.cpp
gpt2_v3.cpp
gptj_v1.cpp
gptj_v2.cpp
gptj_v3.cpp
llama-util.h
llama_v2-util.h
llama_v2.cpp
llama_v2.h
llama_v3.cpp
llama_v3.h
llmutils.cpp	split utils.cpp into 2 files to support sd.cpp	2026-05-04 15:04:12 +08:00
llmutils.h	split utils.cpp into 2 files to support sd.cpp	2026-05-04 15:04:12 +08:00
mpt_v3.cpp
neox_v2.cpp
neox_v3.cpp
otherarch.h	added preliminary support for reasoning budget	2026-04-18 11:56:33 +08:00
rwkv_v2.cpp
rwkv_v2.h
rwkv_v3.cpp
rwkv_v3.h
rwkv_vocab.cpp
tts_adapter.cpp	split utils.cpp into 2 files to support sd.cpp	2026-05-04 15:04:12 +08:00
utils.cpp	split utils.cpp into 2 files to support sd.cpp	2026-05-04 15:04:12 +08:00
utils.h	split utils.cpp into 2 files to support sd.cpp	2026-05-04 15:04:12 +08:00