Skip to content

Revert "Fix spec decoding acc length for dpsk-r1-fp4 tp8" #12900

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
Fridge003 merged 1 commit into from
Nov 9, 2025
Merged

Revert "Fix spec decoding acc length for dpsk-r1-fp4 tp8" #12900

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
4 changes: 2 additions & 2 deletions python/sglang/srt/layers/flashinfer_comm_fusion.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -96,7 +96,7 @@ def cleanup(self):


def ensure_workspace_initialized(
max_token_num: int = 2048, hidden_dim: int = 4096, use_fp32_lamport: bool = False
max_token_num: int = 16384, hidden_dim: int = 4096, use_fp32_lamport: bool = False
Copy link
Contributor

@gemini-code-assist gemini-code-assist bot Nov 9, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

The default value for max_token_num (16384) is used in this function, flashinfer_allreduce_residual_rmsnorm, and fake_flashinfer_allreduce_residual_rmsnorm. To improve maintainability and avoid magic numbers, consider defining this value as a module-level constant (e.g., _DEFAULT_MAX_TOKEN_NUM = 16384) and using this constant in all three function definitions.

):
"""Ensure workspace is initialized"""
if not is_flashinfer_available() or _flashinfer_comm is None:
Expand Down Expand Up @@ -128,7 +128,7 @@ def flashinfer_allreduce_residual_rmsnorm(
residual: torch.Tensor,
weight: torch.Tensor,
eps: float = 1e-6,
max_token_num: int = 2048,
max_token_num: int = 16384,
use_oneshot: Optional[bool] = None,
trigger_completion_at_end: bool = False,
fp32_acc: bool = False,
Expand Down
Loading