Add separate final normalization for Multi-Token Prediction in DeepSeek models. - #5142
Open
copybara-service[bot] wants to merge 1 commit into
Open
Add separate final normalization for Multi-Token Prediction in DeepSeek models.#5142copybara-service[bot] wants to merge 1 commit into
copybara-service[bot] wants to merge 1 commit into
Commits
Commits on Sep 4, 2026
- authored andcommitted