llama.cpp/ggml/src
2024-11-13 19:09:30 +01:00
..
ggml-amx update Makefile 2024-11-12 23:07:50 +01:00
ggml-blas add vulkan and kompute 2024-11-12 18:44:18 +01:00
ggml-cann add amx, cann, sycl 2024-11-12 19:40:25 +01:00
ggml-cpu update Makefile 2024-11-12 23:07:50 +01:00
ggml-cuda add hip 2024-11-12 20:52:46 +01:00
ggml-hip add hip 2024-11-12 20:52:46 +01:00
ggml-kompute add vulkan and kompute 2024-11-12 18:44:18 +01:00
ggml-metal metal : fix build and swift package (#10279) 2024-11-13 15:57:24 +02:00
ggml-musa ggml: build musa backend library (cmake) (#10280) 2024-11-13 19:07:24 +01:00
ggml-rpc add vulkan and kompute 2024-11-12 18:44:18 +01:00
ggml-sycl Merge remote-tracking branch 'origin/master' into sl/dl-backend 2024-11-13 19:09:30 +01:00
ggml-vulkan Merge remote-tracking branch 'origin/master' into sl/dl-backend 2024-11-13 19:09:30 +01:00
CMakeLists.txt ggml: build musa backend library (cmake) (#10280) 2024-11-13 19:07:24 +01:00
ggml-aarch64.c ggml : build backends as libraries 2024-11-11 21:18:27 +01:00
ggml-aarch64.h ggml : build backends as libraries 2024-11-11 21:18:27 +01:00
ggml-alloc.c ggml-alloc : remove buffer_id from leaf_alloc (ggml/987) 2024-10-16 11:28:01 +03:00
ggml-backend-impl.h llama : refactor model loader with backend registry (#10026) 2024-10-30 02:01:23 +01:00
ggml-backend-reg.cpp use reference quantization fns in AMX until moved to CPU backend 2024-11-12 22:06:00 +01:00
ggml-backend.cpp ggml : build backends as libraries 2024-11-11 21:18:27 +01:00
ggml-common.h ggml-quants : ternary packing for TriLMs and BitNet b1.58 (#8151) 2024-09-05 21:48:47 -04:00
ggml-impl.h update Makefile 2024-11-12 23:07:50 +01:00
ggml-quants.c fix tests and examples 2024-11-11 23:44:27 +01:00
ggml-quants.h more build fixes 2024-11-12 13:56:28 +01:00
ggml-threading.cpp ggml : build backends as libraries 2024-11-11 21:18:27 +01:00
ggml-threading.h ggml : build backends as libraries 2024-11-11 21:18:27 +01:00
ggml.c update Makefile 2024-11-12 23:07:50 +01:00