Skip to content

[Bugfix] Remove hardcoded head_size=256 for Deepseek v2 and v3 (#12… #252

[Bugfix] Remove hardcoded head_size=256 for Deepseek v2 and v3 (#12…

[Bugfix] Remove hardcoded head_size=256 for Deepseek v2 and v3 (#12… #252

Annotations

1 warning

clang-format (3.11)

succeeded Jan 16, 2025 in 6s