PR #10446 Refactor/online repacking

Refactor/online repacking #10446

ggerganov merged 9 commits into ggml-org:master from Djip007:refactor/online_repacking

github-actions added ggml

Djip007 commented on 2024-11-21

Djip007 force pushed 1 year ago

Djip007 force pushed 1 year ago

github-actions added Nvidia GPU

github-actions added SYCL

Djip007 force pushed 1 year ago

Djip007 commented on 2024-11-29

Djip007 force pushed 1 year ago

Djip007 marked this pull request as ready for review 1 year ago

slaren commented on 2024-12-02

Djip007 force pushed 1 year ago

slaren commented on 2024-12-04

Djip007 force pushed 1 year ago

github-actions added documentation

github-actions added examples

github-actions added python

Djip007 force pushed 1 year ago

rename ggml-cpu-aarch64.c to .cpp

9ac05c11

reformat extra cpu backend.

98ea414f

clang-format

95322e93

Clean Q4_0_N_M ref

3a042b48

add op GGML_OP_MUL_MAT_ID for Q4_0_N_M with runtime repack

0a2be72d

slaren approved these changes on 2024-12-06

slaren requested a review from

ggerganov 1 year ago

ggerganov approved these changes on 2024-12-06

Djip007 commented on 2024-12-06

added/corrected control on tensor size for Q4 repacking.

b14b4713

Djip007 force pushed to b14b4713 1 year ago

ggerganov commented on 2024-12-07

Update ggml/src/ggml-cpu/ggml-cpu-aarch64.cpp

7dc8a3e2

Update ggml/src/ggml-cpu/ggml-cpu-aarch64.cpp

e115f6f6

add debug logs on repacks.

1221d13d

Djip007 force pushed to 1221d13d 1 year ago

ggerganov merged 19d8762a into master 1 year ago

Reviewers

ggerganov

slaren

Assignees

No one assigned

Labels

documentation Nvidia GPU examples python ggml SYCL

Milestone

No milestone

llama.cpp Refactor/online repacking #10446 Merged

Refactor/online repacking #10446

llama.cpp
Refactor/online repacking
#10446

Merged