Issue Station
Sign In
Tools hereToolbox

transformers - 💡(How to fix) Fix DeepSeek-V4 shared expert not gated.

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
RAW_BUFFERClick to expand / collapse

SwiGLU is not clamped for shared expert. Is it a bug or just a divergence between training and inference?

Deepseek inference ref code: https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash/blob/main/inference/model.py#L627 transformers implementation: https://github.com/huggingface/transformers/blob/main/src/transformers/models/deepseek_v4/modeling_deepseek_v4.py#L1076-L1077

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…
#output truncation#response parsing#generation error#database connection#vector store

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING