Skip to content

Apply deepseek cuda rope #5385

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 8 commits into from
Apr 14, 2025
Merged

Apply deepseek cuda rope #5385

Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
1d497e4
apply deepseek cuda rope
ispobock Apr 14, 2025
6bd2f4f
Merge branch 'main' into fix-ds-rope
ispobock Apr 14, 2025
727726b
Merge branch 'main' into fix-ds-rope
ispobock Apr 14, 2025
a797b11
fix amd pr test
ispobock Apr 14, 2025
0758aed
upd
zhyncs Apr 14, 2025
313e956
test
zhyncs Apr 14, 2025
93f1e4c
Revert "test"
zhyncs Apr 14, 2025
cf2faf5
upd
zhyncs Apr 14, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 12 additions & 1 deletion python/sglang/srt/layers/rotary_embedding.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -645,7 +645,18 @@ def _compute_cos_sin_cache(self) -> torch.Tensor:
cache = torch.cat((cos, sin), dim=-1)
return cache

def forward(
def forward_hip(self, *args, **kwargs):
return self.forward_native(*args, **kwargs)

def forward(self, *args, **kwargs):
if torch._dynamo.is_compiling:
return self.forward_native(*args, **kwargs)
if _is_cuda_available:
return self.forward_cuda(*args, **kwargs)
else:
return self.forward_native(*args, **kwargs)

def forward_native(
self,
positions: torch.Tensor,
query: torch.Tensor,
Expand Down
Loading