Aman Gupta 918e0ad209 CUDA: use LRU based eviction for cuda graphs (llama/21611) ... * CUDA: use a ring-buffer for cuda graphs * bump limit to 128 * use LRU eviction * better naming * do periodic clean-up		2026-04-30 11:29:12 +03:00
..
cmake	cmake : remove unused file (ggml/1419)	2026-02-08 09:29:10 +02:00
include	CUDA: manage NCCL communicators in context (llama/21891)	2026-04-30 11:29:09 +03:00
src	CUDA: use LRU based eviction for cuda graphs (llama/21611)	2026-04-30 11:29:12 +03:00
.gitignore	whisper : reorganize source code + improve CMake (#2256)	2024-06-26 19:34:09 +03:00
CMakeLists.txt	Fix Q8_0 reorder: garbage on 2nd prompt + crash on full VRAM (llama/21638)	2026-04-30 11:29:10 +03:00