Diego Devesa 3420909dff

ggml : automatic selection of best CPU backend (#10606) ...

* ggml : automatic selection of best CPU backend

* amx : minor opt

* add GGML_AVX_VNNI to enable avx-vnni, fix checks

2024-12-01 16:12:41 +01:00

..

amx

ggml : automatic selection of best CPU backend (#10606)

2024-12-01 16:12:41 +01:00

cmake

ggml : build backends as libraries (#10256)

2024-11-14 18:04:35 +01:00

llamafile

ggml : move AMX to the CPU backend (#10570)

2024-11-29 21:54:58 +01:00

CMakeLists.txt

ggml : automatic selection of best CPU backend (#10606)

2024-12-01 16:12:41 +01:00

cpu-feats-x86.cpp

ggml : automatic selection of best CPU backend (#10606)

2024-12-01 16:12:41 +01:00

ggml-cpu-aarch64.c

ggml : automatic selection of best CPU backend (#10606)

2024-12-01 16:12:41 +01:00

ggml-cpu-aarch64.h

ggml-cpu: support IQ4_NL_4_4 by runtime repack (#10541)

2024-11-28 13:52:03 +01:00

ggml-cpu-impl.h

ggml : move AMX to the CPU backend (#10570)

2024-11-29 21:54:58 +01:00

ggml-cpu-quants.c

ggml : fix I8MM Q4_1 scaling factor conversion (#10562)

2024-11-29 16:25:39 +02:00

ggml-cpu-quants.h

ggml : build backends as libraries (#10256)

2024-11-14 18:04:35 +01:00

ggml-cpu.c

ggml : move AMX to the CPU backend (#10570)

2024-11-29 21:54:58 +01:00

ggml-cpu.cpp

ggml : move AMX to the CPU backend (#10570)

2024-11-29 21:54:58 +01:00