Skip to content

fix: zero-init fp32 UE8M0 activation scales in the gemm1_alpha masked path #32386

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
yueming-yuan wants to merge 1 commit into
base: main
Choose a base branch
from
+2 −1
Open

fix: zero-init fp32 UE8M0 activation scales in the gemm1_alpha masked path #32386

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
3 changes: 2 additions & 1 deletion python/sglang/srt/layers/moe/moe_runner/deep_gemm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -966,7 +966,8 @@ def _varlen_deep_gemm_silu_mul_quant(
down_input = torch.empty(
(E, N, D), device=hidden_states_device, dtype=torch.float8_e4m3fn
)
down_input_scale = torch.empty(
alloc = torch.empty if use_packed else torch.zeros
down_input_scale = alloc(
(E, G // 4, N) if use_packed else (E, N, G),
device=hidden_states_device,
dtype=torch.int32 if use_packed else torch.float32,
Expand Down
Loading