[GH-ISSUE #374] [DSv4] IS W4A16(mxfp4, act bf16) on the planning list? #180

Open
opened 2026-10-26 21:14:17 +00:00 by bsakaguchi · 0 comments
Owner

Originally created by @heroes999 on GitHub (Jul 6, 2026).
Original GitHub issue: https://github.com/deepseek-ai/DeepGEMM/issues/374

For Hopper, SGLang supports both w8a8 and w4a16 path. The latter path supports only marlin/flashinfer_mxfp4. So is there any plan to support this fea in DeepGeMM?

Originally created by @heroes999 on GitHub (Jul 6, 2026). Original GitHub issue: https://github.com/deepseek-ai/DeepGEMM/issues/374 For Hopper, SGLang supports both w8a8 and w4a16 path. The latter path supports only marlin/flashinfer_mxfp4. So is there any plan to support this fea in DeepGeMM?
Sign in to join this conversation.
No labels
pull-request
No milestone
No project
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
deepseek-ai/DeepGEMM#180
No description provided.