Skip to content

support TBO decode in Deepseek v4 #1275

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

Open
ZhangLirong-amd wants to merge 3 commits into
base: main
Choose a base branch
from
Open

support TBO decode in Deepseek v4 #1275

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
e54428e
support TBO decode in Deepseek v4
ZhangLirong-amd Jun 18, 2026
b4b3b7e
format
ZhangLirong-amd Jun 18, 2026
0264532
format
ZhangLirong-amd Jun 18, 2026
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
4 changes: 2 additions & 2 deletions atom/model_engine/model_runner.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2311,9 +2311,9 @@ def capture_cudagraph(self):
context.positions = mrope_positions
num_pad, num_tokens_across_dp = self.get_dp_padding(num_tokens)
num_tokens += num_pad
# Create ubatch slices for TBO capture (need >= 2 requests)
# Create ubatch slices for TBO capture (need > 2 requests)
ubatch_slices = None
if is_tbo and self.config.enable_tbo_decode and bs >= 2:
if is_tbo and self.config.enable_tbo_decode and bs > 2:
ubatch_slices = maybe_create_ubatch_slices(
Comment on lines +2314 to 2317
num_reqs=bs,
num_tokens=num_tokens,
Expand Down
Loading
Loading