Tiny fix trtllm_fp8_per_tensor_scale_moe_wrapper router_logits dtype#22006
Merged
Qiaolin-Yu merged 2 commits intomainfrom Apr 6, 2026
Merged
Tiny fix trtllm_fp8_per_tensor_scale_moe_wrapper router_logits dtype#22006Qiaolin-Yu merged 2 commits intomainfrom
Qiaolin-Yu merged 2 commits intomainfrom
Conversation
Qiaolin-Yu
requested review from
BBuf,
Edwardf0t1,
Fridge003,
HaiShaw,
Ying1123,
ch-wan,
ispobock and
merrymercy
as code owners
Contributor
|
Warning You have reached your daily quota limit. Please wait up to 24 hours and I will start processing your requests again! |
Collaborator
Author
|
/tag-and-rerun-ci |
b8zhong
approved these changes
Apr 4, 2026
Collaborator
|
Btw, This bug happen before (#14350 also maybe one more instance but I can't find it...) |
nvpohanh
reviewed
Apr 6, 2026
| # during torch.compile for piecewise cuda graph. | ||
| # Use custom op wrapper for torch.compile compatibility. | ||
|
|
||
| # The DeepSeekV3 routing method requires float32 router logits. |
Collaborator
Collaborator
There was a problem hiding this comment.
Maybe will be fixed by flashinfer-ai/flashinfer#2993 ?
Collaborator
There was a problem hiding this comment.
The path for block scale had this fix already, I think we didn't use per tensor scaling before?
Collaborator
There was a problem hiding this comment.
got it. we have never run DSV3/R1 with per-tensor FP8 before.
JustinTong0323
pushed a commit
to JustinTong0323/sglang
that referenced
this pull request
Apr 7, 2026
Fridge003
pushed a commit
that referenced
this pull request
Apr 7, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
5 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Motivation
https://github.com/flashinfer-ai/flashinfer/blob/fe0539318dcc31c76a33a7ed2ab0ee3c94fe6bad/csrc/trtllm_fused_moe_kernel_launcher.cu#L1789
the dtype of router_logits should be float32 for deepseek routing method
Modifications
Accuracy Tests
Speed Tests and Profiling
Checklist
Review and Merge Process
/tag-and-rerun-ci,/tag-run-ci-label,/rerun-failed-ci