llama.cpp
sycl: quantize and reorder the input to q8_1 when reorder is enabled
#13826
Merged

sycl: quantize and reorder the input to q8_1 when reorder is enabled #13826

AD2605
AD2605 [WIP]: fuse q8 quantization and reorder
0d71ffaa
AD2605 wip2: fuse q8 quantization and reorder
6096ff80
AD2605 working q8 reorder commit
acd80eca
AD2605 restored common.hpp
03bd1a6c
AD2605 Merge remote-tracking branch 'origin/master' into ad/quantize_and_reo…
7903264e
AD2605 remove debug prints
ade12bf5
github-actions github-actions added ggml
github-actions github-actions added SYCL
Alcpz
Alcpz commented on 2025-05-28
AD2605 remove unnecessary headers and remove trailing whitespace
79eede6c
AD2605 Update ggml/src/ggml-sycl/ggml-sycl.cpp
5f8bc743
Alcpz
Alcpz approved these changes on 2025-05-29
Rbiessy
Rbiessy approved these changes on 2025-05-30
Alcpz Alcpz merged 663445b0 into master 131 days ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone