llama.cpp
Support multiple GPUs (split mode) on SYCL backend
#5806
Merged
Overview
Commits
7
Changes
View On GitHub

Support multiple GPUs (split mode) on SYCL backend #5806

NeoZhangJianyu merged 7 commits into ggml-org:master from NeoZhangJianyu:mulcards
NeoZhangJianyu
NeoZhangJianyu suport multiple cards: split-mode - layer|row
f87da8eb
NeoZhangJianyu rm warning
33563a8a
NeoZhangJianyu rebase with master, support tow new OPs, close feature for -sm=row, f…
4c29df30
NeoZhangJianyu update news
47a572df
NeoZhangJianyu Merge branch 'master' into mulcards
6b010680
NeoZhangJianyu NeoZhangJianyu requested a review from ggerganov ggerganov 1 year ago
NeoZhangJianyu NeoZhangJianyu requested a review from slaren slaren 1 year ago
NeoZhangJianyu
NeoZhangJianyu fix merge error
5db8896f
slaren
slaren commented on 2024-03-01
slaren
slaren approved these changes on 2024-03-01
ggerganov
ggerganov approved these changes on 2024-03-01
NeoZhangJianyu update according to review comments
e4cc4121
NeoZhangJianyu NeoZhangJianyu merged 71564139 into master 1 year ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
None yet
Milestone
No milestone
Terms Of Use Privacy Policy Refund Policy Impressum