llama.cpp/ggml/src/ggml-cpu/arch
Christian Kastner 6369be0735
Implement GGML_CPU_ALL_VARIANTS for PowerPC (#14286)
* Add PowerPC feature detection and scoring

* ggml-cpu: Implement GGML_CPU_ALL_VARIANTS for PowerPC

* ggml-cpu: Delay some initializations until function is called

When using GGML_BACKEND_DL=ON, these initializations might use
instructions that are not supported by the current CPU.

---------

Co-authored-by: Diego Devesa <slarengh@gmail.com>
2025-06-20 14:17:32 +02:00
..
arm ggml-cpu : remove unnecesary arm feature detection (#14281) 2025-06-19 21:24:14 +02:00
loongarch ggml-cpu : split arch-specific implementations (#13892) 2025-06-09 16:47:13 +02:00
powerpc Implement GGML_CPU_ALL_VARIANTS for PowerPC (#14286) 2025-06-20 14:17:32 +02:00
riscv ggml-cpu : split arch-specific implementations (#13892) 2025-06-09 16:47:13 +02:00
s390 ggml-cpu : split arch-specific implementations (#13892) 2025-06-09 16:47:13 +02:00
wasm ggml-cpu : split arch-specific implementations (#13892) 2025-06-09 16:47:13 +02:00
x86 ggml-cpu : split arch-specific implementations (#13892) 2025-06-09 16:47:13 +02:00