[model] feat: Backport DeepSeek V4 Bridge - #30
Draft
bobboli wants to merge 2 commits into
Draft
Conversation
Backport of NVIDIA-NeMo#3562. Co-authored-by: chcui <chcui@nvidia.com> Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
…-NeMo#4271) Backport of NVIDIA-NeMo#4271. Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
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
3 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
The model bridge supports direct Hugging Face import for the DeepSeek V4 FP8 and MXFP4 checkpoint layouts, including its model-local dequantization and
tid2eidmapping paths.This is a minimal backport onto
bridge. It intentionally excludes the unrelated shared dequantization refactor and the latercompress_rope_thetaprecedence change.Verification
python -m pytest tests/unit_tests/models/deepseek/test_deepseek_v4_bridge.py -q: 15 passed