Oliver Simons 7668999518 Merge branch 'master' into gpu-sampling ... Let's keep `master's` cumsum implementation for it's likely better AMD perf and add back pure-CUB-implementation in follow-up commit		2025-12-05 14:41:08 +01:00
..
batched-bench	batched-bench : add "separate text gen" mode (#17103)	2025-11-10 12:59:29 +02:00
cvector-generator	refactor : simplify and improve memory management	2025-11-28 16:09:42 +02:00
export-lora	cmake : Do not install tools on iOS targets (#15903)	2025-09-16 09:54:44 +07:00
gguf-split	ci : use smaller model (#16168)	2025-09-22 09:11:39 +03:00
imatrix	refactor : simplify and improve memory management	2025-11-28 16:09:42 +02:00
llama-bench	bench : cache the llama_context state at computed depth (#16944)	2025-11-07 21:23:11 +02:00
main	Merge branch 'master' into HEAD	2025-12-01 14:47:50 +02:00
mtmd	Merge remote-tracking branch 'upstream/master' into backend-sampling	2025-12-04 08:17:50 +01:00
perplexity	refactor : simplify and improve memory management	2025-11-28 16:09:42 +02:00
quantize	ci : use smaller model (#16168)	2025-09-22 09:11:39 +03:00
rpc	Install rpc-server when GGML_RPC is ON. (#17149)	2025-11-11 10:53:59 +00:00
run	Manually link -lbsd to resolve flock symbol on AIX (#16610)	2025-10-23 19:37:31 +08:00
server	Merge branch 'master' into gpu-sampling	2025-12-05 14:41:08 +01:00
tokenize	cmake : Do not install tools on iOS targets (#15903)	2025-09-16 09:54:44 +07:00
tts	refactor : simplify and improve memory management	2025-11-28 16:09:42 +02:00
CMakeLists.txt	mtmd : rename llava directory to mtmd (#13311)	2025-05-05 16:02:55 +02:00