llama.cpp/ggml/src/ggml-metal
Georgi Gerganov dfcd53f7ec
metal : fuse NORM + MUL + ADD, support non-multiples of 4 (#16220)
* metal : fuse NORM + MUL + ADD

* metal : support norms of non-multiple of 4

* cont : fix comment [no ci]
2025-09-25 11:30:16 +03:00
..
CMakeLists.txt metal : refactor + optimize v2 (#15995) 2025-09-17 20:38:12 +03:00
ggml-metal-common.cpp metal : fuse NORM + MUL + ADD, support non-multiples of 4 (#16220) 2025-09-25 11:30:16 +03:00
ggml-metal-common.h metal : refactor + optimize v2 (#15995) 2025-09-17 20:38:12 +03:00
ggml-metal-context.h metal : refactor + optimize v2 (#15995) 2025-09-17 20:38:12 +03:00
ggml-metal-context.m metal : refactor + optimize v2 (#15995) 2025-09-17 20:38:12 +03:00
ggml-metal-device.cpp metal : fuse NORM + MUL + ADD, support non-multiples of 4 (#16220) 2025-09-25 11:30:16 +03:00
ggml-metal-device.h metal : fuse NORM + MUL + ADD, support non-multiples of 4 (#16220) 2025-09-25 11:30:16 +03:00
ggml-metal-device.m metal : fuse NORM + MUL + ADD, support non-multiples of 4 (#16220) 2025-09-25 11:30:16 +03:00
ggml-metal-impl.h metal : fuse NORM + MUL + ADD, support non-multiples of 4 (#16220) 2025-09-25 11:30:16 +03:00
ggml-metal-ops.cpp metal : fuse NORM + MUL + ADD, support non-multiples of 4 (#16220) 2025-09-25 11:30:16 +03:00
ggml-metal-ops.h metal : fuse NORM + MUL + ADD, support non-multiples of 4 (#16220) 2025-09-25 11:30:16 +03:00
ggml-metal.cpp rename optimize_graph to graph_optimize (#16082) 2025-09-18 13:46:17 -05:00
ggml-metal.metal metal : fuse NORM + MUL + ADD, support non-multiples of 4 (#16220) 2025-09-25 11:30:16 +03:00