Support multiple GPUs (split mode) on SYCL backend (llama/5806)

Browse Source

* suport multiple cards: split-mode - layer|row

* rm warning

* rebase with master, support tow new OPs, close feature for -sm=row, fix for unit test

* update news

* fix merge error

* update according to review comments

...

This commit is contained in:

Neo Zhang Jianyu

2024-03-02 19:49:30 +08:00

committed by Georgi Gerganov

parent 422a6b16fc

commit c3bfc9bfda

2 changed files with 1421 additions and 789 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

2205

ggml-sycl.cpp

File diff suppressed because it is too large Load Diff