llamacpp/llama.cpp/ggml/src/ggml-cpu/ Source Tree

../
[+] amx/
[+] arch/
arch-fallback.h
binary-ops.cpp
binary-ops.h
common.h type_conversion_table
ggml-cpu-impl.h
ggml-cpu.c ggml_compute_state ggml_numa_node ggml_numa_nodes ggml_state ggml_threadpool mmid_row_mapping
ggml-cpu.cpp ggml_backend_cpu_context ggml_backend_cpu_device_context ggml_backend_plan_cpu
hbm.cpp
[+] llamafile/
ops.cpp ggml_conv_2d_dw_params
ops.h
quants.c
quants.h
repack.cpp extra_buffer_type tensor_traits tensor_traits_base
repack.h block block_iq4_nlx4 block_iq4_nlx8 block_q2_Kx8 block_q4_Kx8 block_q8_Kx4
simd-mappings.h
traits.cpp
traits.h extra_buffer_type tensor_traits
unary-ops.cpp
unary-ops.h
vec.cpp
vec.h

Browse the source code of llamacpp/llama.cpp/ggml/src/ggml-cpu/ online