llama.cpp
ggml-cpu : split arch-specific implementations
#13892
Merged
Overview
Commits
56
Changes
View On GitHub

ggml-cpu : split arch-specific implementations #13892

slaren merged 56 commits into ggml-org:master from xctan:split-arch
xctan
xctan
xctan xctan force pushed 194 days ago
github-actions github-actions added ggml
xctan xctan force pushed 193 days ago
xctan xctan marked this pull request as ready for review 193 days ago
xctan
ggerganov ggerganov requested a review from ggerganov ggerganov 188 days ago
ggerganov
ggerganov commented on 2025-06-04
ggerganov
ggerganov commented on 2025-06-04
ggerganov
ggerganov commented on 2025-06-04
github-actions github-actions added Nvidia GPU
github-actions github-actions added SYCL
ggerganov
ggerganov commented on 2025-06-05
ggerganov
xctan move ggml-cpu-aarch64 to repack
6814bd48
xctan split quantize_row_q8_0/1
a07340a1
xctan split helper functions
82d7410f
xctan split ggml_vec_dot_q4_0_q8_0
ead57621
xctan split ggml_vec_dot_q4_1_q8_1
627e1ecd
xctan split ggml_vec_dot_q5_0_q8_0
9582518e
xctan split ggml_vec_dot_q5_1_q8_1
beca2195
xctan split ggml_vec_dot_q8_0_q8_0
a32715a8
xctan split ggml_vec_dot_tq1_0_q8_K
a46eca7d
xctan split ggml_vec_dot_tq2_0_q8_K
96a7f516
xctan split ggml_vec_dot_q2_K_q8_K
5f881c9f
xctan split ggml_vec_dot_q3_K_q8_K
91fbf27d
xctan split ggml_vec_dot_q4_K_q8_K
58b6c627
xctan split ggml_vec_dot_q5_K_q8_K
6272e0cc
xctan split ggml_vec_dot_q6_K_q8_K
7c7223f2
xctan split ggml_vec_dot_iq2_xxs_q8_K
9671c0e2
xctan split ggml_vec_dot_iq2_xs_q8_K
e4e1cfc2
xctan split ggml_vec_dot_iq2_s_q8_K
c9efc9ee
xctan split ggml_vec_dot_iq3_xxs_q8_K
d1d2e24d
xctan split ggml_vec_dot_iq3_s_q8_K
da6fcec8
xctan split ggml_vec_dot_iq1_s_q8_K
3334b107
xctan split ggml_vec_dot_iq1_m_q8_K
93f0c4f6
xctan split ggml_vec_dot_iq4_nl_q8_0
3f4866f5
xctan split ggml_vec_dot_iq4_xs_q8_K
740b3c9f
xctan fix typos
9487b769
xctan fix missing prototypes
88e7e42a
xctan rename ggml-cpu-quants.c
2252aa2b
xctan rename ggml-cpu-traits
6df3dd57
xctan rename arm folder
3566ee8d
xctan move cpu-feats-x86.cpp
f40ad8c9
xctan rename ggml-cpu-hbm
1ac2d5ec
xctan update arm detection macro in quants.c
321b3ac4
xctan move iq quant tables
7b5bf50f
xctan split ggml_quantize_mat_q8_0/K
bf3dbea0
xctan split ggml_gemv_*
868c895c
xctan split ggml_gemm_*
6a2ba77c
xctan rename namespace aarch64 to repack
72ddf5ad
xctan use weak aliases to replace test macros
ad523494
xctan rename GGML_CPU_AARCH64 to GGML_CPU_REPACK
62dc3fd8
xctan rename more aarch64 to repack
46b1e49e
xctan clean up rebase leftover
5601df65
xctan fix compilation errors
827aec0d
xctan remove trailing spaces
58210b8c
xctan try to fix clang compilation errors
2739f4c5
xctan try to fix clang compilation errors again
8713f877
xctan try to fix clang compilation errors, 3rd attempt
df278103
xctan try to fix clang compilation errors, 4th attempt
553d8ca6
xctan try to fix clang compilation errors, 5th attempt
9bfcd7e2
xctan try to fix clang compilation errors, 6th attempt
08ebdd91
xctan try to fix clang compilation errors, 7th attempt
67eceec5
xctan try to fix clang compilation errors, 8th attempt
01a1c5c0
xctan try to fix clang compilation errors, 9th attempt
bef5b8d1
xctan more cleanup
47701d51
xctan fix compilation errors
e5b6fdb7
xctan fix apple targets
2573662f
xctan fix a typo in arm version of ggml_vec_dot_q4_K_q8_K
93e6718b
xctan xctan force pushed to 93e6718b 187 days ago
ggerganov
ggerganov approved these changes on 2025-06-06
ggerganov ggerganov requested a review from slaren slaren 186 days ago
slaren
slaren approved these changes on 2025-06-09
slaren slaren merged f470bc36 into master 183 days ago
l15y
ggerganov
l15y
xctan
barracuda156

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Nvidia GPU ggml SYCL
Milestone
No milestone
Terms Of Use Privacy Policy Refund Policy Impressum