Add llama converter (no dependency on internal Nvidia code) - part 1/2#545
Merged
danielkorzekwa merged 19 commits intofeature/compressfrom Nov 13, 2025
Merged
Conversation
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
…ntained Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
Comment on lines
+30
to
+37
| from puzzle_tools import deci_lm_hf_code | ||
| from puzzle_tools.common import infer_weights_dtype | ||
| from puzzle_tools.deci_lm_hf_code.configuration_decilm import DeciLMConfig | ||
| from puzzle_tools.deci_lm_hf_code.modeling_decilm import DeciLMForCausalLM | ||
| from puzzle_tools.robust_json import json_dumps | ||
| from safetensors.torch import save_file as safe_save_file | ||
| from transformers.utils import SAFE_WEIGHTS_INDEX_NAME | ||
| from utils.post_init_sparse import SparsityMethod |
Collaborator
There was a problem hiding this comment.
decilm imports need to be fixed to modelopt path
Contributor
Author
There was a problem hiding this comment.
this is done in 2/2, see scope of 1/2 in MR description.
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## feature/compress #545 +/- ##
=================================================
Coverage 73.40% 73.40%
=================================================
Files 180 180
Lines 18127 18127
=================================================
Hits 13306 13306
Misses 4821 4821 ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
kevalmorabia97
approved these changes
Nov 13, 2025
…ntained Signed-off-by: Daniel Korzekwa <dkorzekwa@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
2 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.
What does this PR do?
Add llama converter (no dependency on internal Nvidia code) - part 1/2
scope of 2/2 part (will come once part 1/2 is merged):