]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
ggml-cpu : split arch-specific implementations (#13892)
authorxctan <redacted>
Mon, 9 Jun 2025 14:47:13 +0000 (22:47 +0800)
committerGitHub <redacted>
Mon, 9 Jun 2025 14:47:13 +0000 (16:47 +0200)
commitf470bc36bed4d836b9de5a483fa0dfaee176d6f5
tree3a82619a28973086e6d1067a760b0ed915515136
parent8f47e25f56e9792093b7497c68e9f80bab82ed19
ggml-cpu : split arch-specific implementations (#13892)

* move ggml-cpu-aarch64 to repack

* split quantize_row_q8_0/1

* split helper functions

* split ggml_vec_dot_q4_0_q8_0

* split ggml_vec_dot_q4_1_q8_1

* split ggml_vec_dot_q5_0_q8_0

* split ggml_vec_dot_q5_1_q8_1

* split ggml_vec_dot_q8_0_q8_0

* split ggml_vec_dot_tq1_0_q8_K

* split ggml_vec_dot_tq2_0_q8_K

* split ggml_vec_dot_q2_K_q8_K

* split ggml_vec_dot_q3_K_q8_K

* split ggml_vec_dot_q4_K_q8_K

* split ggml_vec_dot_q5_K_q8_K

* split ggml_vec_dot_q6_K_q8_K

* split ggml_vec_dot_iq2_xxs_q8_K

* split ggml_vec_dot_iq2_xs_q8_K

* split ggml_vec_dot_iq2_s_q8_K

* split ggml_vec_dot_iq3_xxs_q8_K

* split ggml_vec_dot_iq3_s_q8_K

* split ggml_vec_dot_iq1_s_q8_K

* split ggml_vec_dot_iq1_m_q8_K

* split ggml_vec_dot_iq4_nl_q8_0

* split ggml_vec_dot_iq4_xs_q8_K

* fix typos

* fix missing prototypes

* rename ggml-cpu-quants.c

* rename ggml-cpu-traits

* rename arm folder

* move cpu-feats-x86.cpp

* rename ggml-cpu-hbm

* update arm detection macro in quants.c

* move iq quant tables

* split ggml_quantize_mat_q8_0/K

* split ggml_gemv_*

* split ggml_gemm_*

* rename namespace aarch64 to repack

* use weak aliases to replace test macros

* rename GGML_CPU_AARCH64 to GGML_CPU_REPACK

* rename more aarch64 to repack

* clean up rebase leftover

* fix compilation errors

* remove trailing spaces

* try to fix clang compilation errors

* try to fix clang compilation errors again

* try to fix clang compilation errors, 3rd attempt

* try to fix clang compilation errors, 4th attempt

* try to fix clang compilation errors, 5th attempt

* try to fix clang compilation errors, 6th attempt

* try to fix clang compilation errors, 7th attempt

* try to fix clang compilation errors, 8th attempt

* try to fix clang compilation errors, 9th attempt

* more cleanup

* fix compilation errors

* fix apple targets

* fix a typo in arm version of ggml_vec_dot_q4_K_q8_K

Co-authored-by: Georgi Gerganov <redacted>
---------

Co-authored-by: Georgi Gerganov <redacted>
42 files changed:
Makefile
ggml/CMakeLists.txt
ggml/src/ggml-common.h
ggml/src/ggml-cpu/CMakeLists.txt
ggml/src/ggml-cpu/amx/amx.cpp
ggml/src/ggml-cpu/amx/mmq.cpp
ggml/src/ggml-cpu/arch/arm/quants.c [new file with mode: 0644]
ggml/src/ggml-cpu/arch/arm/repack.cpp [new file with mode: 0644]
ggml/src/ggml-cpu/arch/loongarch/quants.c [new file with mode: 0644]
ggml/src/ggml-cpu/arch/powerpc/quants.c [new file with mode: 0644]
ggml/src/ggml-cpu/arch/riscv/quants.c [new file with mode: 0644]
ggml/src/ggml-cpu/arch/riscv/repack.cpp [new file with mode: 0644]
ggml/src/ggml-cpu/arch/s390/quants.c [new file with mode: 0644]
ggml/src/ggml-cpu/arch/wasm/quants.c [new file with mode: 0644]
ggml/src/ggml-cpu/arch/x86/cpu-feats.cpp [new file with mode: 0644]
ggml/src/ggml-cpu/arch/x86/quants.c [new file with mode: 0644]
ggml/src/ggml-cpu/arch/x86/repack.cpp [new file with mode: 0644]
ggml/src/ggml-cpu/common.h
ggml/src/ggml-cpu/cpu-feats-x86.cpp [deleted file]
ggml/src/ggml-cpu/ggml-cpu-aarch64.cpp [deleted file]
ggml/src/ggml-cpu/ggml-cpu-aarch64.h [deleted file]
ggml/src/ggml-cpu/ggml-cpu-hbm.cpp [deleted file]
ggml/src/ggml-cpu/ggml-cpu-hbm.h [deleted file]
ggml/src/ggml-cpu/ggml-cpu-impl.h
ggml/src/ggml-cpu/ggml-cpu-quants.c [deleted file]
ggml/src/ggml-cpu/ggml-cpu-quants.h [deleted file]
ggml/src/ggml-cpu/ggml-cpu-traits.cpp [deleted file]
ggml/src/ggml-cpu/ggml-cpu-traits.h [deleted file]
ggml/src/ggml-cpu/ggml-cpu.c
ggml/src/ggml-cpu/ggml-cpu.cpp
ggml/src/ggml-cpu/hbm.cpp [new file with mode: 0644]
ggml/src/ggml-cpu/hbm.h [new file with mode: 0644]
ggml/src/ggml-cpu/kleidiai/kleidiai.cpp
ggml/src/ggml-cpu/quants.c [new file with mode: 0644]
ggml/src/ggml-cpu/quants.h [new file with mode: 0644]
ggml/src/ggml-cpu/repack.cpp [new file with mode: 0644]
ggml/src/ggml-cpu/repack.h [new file with mode: 0644]
ggml/src/ggml-cpu/traits.cpp [new file with mode: 0644]
ggml/src/ggml-cpu/traits.h [new file with mode: 0644]
ggml/src/ggml-cuda/common.cuh
ggml/src/ggml-quants.c
ggml/src/ggml-sycl/common.hpp