[SYCL] Support Q4_1, Q5_0, Q5_1 in Flash-attention (#23812)

Browse Source

* support Q4_1, Q5_0, Q5_1

* update ut case

...

This commit is contained in:

Neo Zhang

2026-06-01 09:53:53 +03:00

committed by GitHub

parent 4162522688

commit a51142497a

3 changed files with 1016 additions and 1015 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

docs/ops/SYCL.csv

+1012 -1012

File diff suppressed because it is too large Load Diff