Skip to content

[BugFix][KVCache][Speculative Decoding] Fix get_max_chunk_tokens for PD-split decode node in MTP scenario #7756

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
yuanlehome merged 1 commit into from
May 9, 2026
+7 −1
Merged

[BugFix][KVCache][Speculative Decoding] Fix get_max_chunk_tokens for PD-split decode node in MTP scenario #7756

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
8 changes: 7 additions & 1 deletion fastdeploy/config.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2506,7 +2506,13 @@ def get_max_chunk_tokens(self, mm_max_tokens_per_item=None):
if paddle.is_compiled_with_xpu():
num_tokens = self.scheduler_config.max_num_batched_tokens
else:
num_tokens = self.scheduler_config.max_num_seqs
# In MTP scenario, each sequence generates (num_speculative_tokens + 1) tokens per step
mtp_steps = (
(getattr(self.speculative_config, "num_speculative_tokens", 0) + 1)
if self.speculative_config is not None and self.speculative_config.method is not None
else 1
)
num_tokens = self.scheduler_config.max_num_seqs * mtp_steps
else:
num_tokens = self.scheduler_config.max_num_batched_tokens
if self.enable_mm_runtime and mm_max_tokens_per_item is not None:
Expand Down
Loading