[Doge] `DogeCDMoE` router `.view(2, bsz * seq_len, -1)` mixes tokens: with `is_moe=True`, logits depend on future tokens and on other sequences in the batch
Public issue #50230 in huggingface/transformers. The source issue contains the full report and discussion.
Read original source![Source reference for [Doge] `DogeCDMoE` router `.view(2, bsz * seq_len, -1)` mixes tokens: with `is_moe=True`, logits depend on future tokens and on other sequences in the batch. Screenshot not yet available.](/media/daf312744e3a23f0d585271f)
Source record
Research analysis
Reported problem
The record contains the title “[Doge] `DogeCDMoE` router `.view(2, bsz * seq_len, -1)` mixes tokens: with `is_moe=True`, logits depend on future tokens and on other sequences in the batch” but no substantive source summary.
Frequency & alternatives
This is one problem record. Independent user counts, task frequency and existing spending have not been established.
Demand hypothesis
Treat the reported task or obstacle as an interview lead. A feature request, complaint or search for alternatives does not by itself identify a budget owner or willingness to pay.
Commercial evidence gaps
Missing evidence: distinct affected users, repeated occasions, current workaround, measured time or money cost, purchasing authority and a response to a concrete offer.
Validation decision
Group original reports by the same task and deduplicate authors and reposts. Ask how the task is handled today and what it costs; test a defined offer before claiming paid demand.