feat(modelopt): add format-general real-quant vLLM rollout - #3945
Draft
mxinO wants to merge 16 commits into
Draft
Conversation
Signed-off-by: Meng Xin <mxin@nvidia.com>
Signed-off-by: Meng Xin <mxin@nvidia.com>
Signed-off-by: Meng Xin <mxin@nvidia.com>
Signed-off-by: Meng Xin <mxin@nvidia.com>
Signed-off-by: Meng Xin <mxin@nvidia.com>
Signed-off-by: Meng Xin <mxin@nvidia.com>
Signed-off-by: Meng Xin <mxin@nvidia.com>
Signed-off-by: Meng Xin <mxin@nvidia.com>
Signed-off-by: Meng Xin <mxin@nvidia.com>
Signed-off-by: Meng Xin <mxin@nvidia.com>
…nt-refit Signed-off-by: Meng Xin <mxin@nvidia.com> # Conflicts: # tests/unit/algorithms/test_grpo.py
Signed-off-by: Meng Xin <mxin@nvidia.com>
Signed-off-by: Meng Xin <mxin@nvidia.com>
Signed-off-by: Meng Xin <mxin@nvidia.com>
|
Auto-sync is disabled for draft pull requests in this repository. Workflows must be run manually. Contributors can view more details about this message here. |
github-actions
Bot
added
the
Documentation
mxinO
changed the title
Signed-off-by: Meng Xin <mxin@nvidia.com>
Signed-off-by: Meng Xin <mxin@nvidia.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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
This PR extends NeMo-RL native real-quant rollout from a hard-coded NVFP4 path to canonical ModelOpt formats.
A format is available for rollout when ModelOpt can functionally export its canonical tensors and the pinned vLLM ModelOpt loader accepts that exact schema. Unsupported formats fail during setup rather than silently falling back.
Dependencies
The ModelOpt and Megatron-Bridge pins will be updated after the dependency APIs land.
Validation
This remains a draft while dependency pins and exact mixed-format runtime qualification are pending.