Awni Hannun c4230747a1 redesign for faster cpu/gpu synch (#1869) ... * redesign for faster cpu/gpu synch * load + more async CPU * use command encoder API and move more ops to use it * make fence back-end generic + CPU only fence * faster build * fix async eval * fixes + handle temporaries * fix / improve cpu conv * remove unused status, fix siblings * fix extensions * fix * fix no cpu build * format * comments * fix perf regression, remove unecessary abort * fix events, task limit cpu * fix waiting * fix donation / temporaries in normalization		2025-03-06 19:23:38 -08:00
..
CMakeLists.txt	always use json (#1938)	2025-03-06 15:35:56 -08:00
gguf_quants.cpp	More shape type (#1705)	2024-12-19 08:08:20 -08:00
gguf.cpp	More shape type (#1705)	2024-12-19 08:08:20 -08:00
gguf.h	More shape type (#1705)	2024-12-19 08:08:20 -08:00
load.cpp	redesign for faster cpu/gpu synch (#1869)	2025-03-06 19:23:38 -08:00
load.h	Ring distributed backend (#1784)	2025-01-27 22:15:01 -08:00
no_gguf.cpp	Add compiler flags to disable safetensors and gguf (#1098)	2024-05-09 17:39:44 -07:00
no_safetensors.cpp	Add compiler flags to disable safetensors and gguf (#1098)	2024-05-09 17:39:44 -07:00
safetensors.cpp	redesign for faster cpu/gpu synch (#1869)	2025-03-06 19:23:38 -08:00