Diego Devesa a815940e0e ggml : add predefined list of CPU backend variants to build (llama/10626) ...

* ggml : add predefined list of CPU backend variants to build

* update CPU dockerfiles

2024-12-08 20:14:35 +02:00

..

amx

files : remove make artifacts

2024-12-08 20:14:35 +02:00

cmake

ggml : build backends as libraries (llama/10256)

2024-11-20 21:00:08 +02:00

llamafile

ggml : move AMX to the CPU backend (llama/10570)

2024-12-08 20:14:35 +02:00

CMakeLists.txt

ggml : add predefined list of CPU backend variants to build (llama/10626)

2024-12-08 20:14:35 +02:00

cpu-feats-x86.cpp

ggml : add predefined list of CPU backend variants to build (llama/10626)

2024-12-08 20:14:35 +02:00

ggml-cpu-aarch64.c

ggml : move AMX to the CPU backend (llama/10570)

2024-12-08 20:14:35 +02:00

ggml-cpu-aarch64.h

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

2024-12-08 20:14:35 +02:00

ggml-cpu-impl.h

ggml : move AMX to the CPU backend (llama/10570)

2024-12-08 20:14:35 +02:00

ggml-cpu-quants.c

ggml : fix I8MM Q4_1 scaling factor conversion (llama/10562)

2024-12-08 20:14:35 +02:00

ggml-cpu-quants.h

ggml : build backends as libraries (llama/10256)

2024-11-20 21:00:08 +02:00

ggml-cpu.c

ggml : add predefined list of CPU backend variants to build (llama/10626)

2024-12-08 20:14:35 +02:00

ggml-cpu.cpp

ggml : add predefined list of CPU backend variants to build (llama/10626)

2024-12-08 20:14:35 +02:00