TRT-LLM export P-tuning related fixes #8863
Merged
Conversation
This file contains 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
Signed-off-by: Alexey Panteleev <alpanteleev@nvidia.com>
Signed-off-by: Alexey Panteleev <alpanteleev@nvidia.com>
- Remember the vtoken counts for each p-tuning table when the tables are added; - Prepend the right number of vtokens to each query based on its task_id; - Preserve the dtype of the p-tuning table when it is padded; - Validate that all p-tuning tables fit into max_prompt_embedding_table_size limit. Signed-off-by: Alexey Panteleev <alpanteleev@nvidia.com>
oyilmaz-nvidia
approved these changes
May 2, 2024
suiyoubi
pushed a commit
that referenced
this pull request
May 2, 2024
* Fixed the uses of pathlib.Path. Signed-off-by: Alexey Panteleev <alpanteleev@nvidia.com> * Add the bos token to LLAMA based models. Signed-off-by: Alexey Panteleev <alpanteleev@nvidia.com> * P-tuning related fixes: - Remember the vtoken counts for each p-tuning table when the tables are added; - Prepend the right number of vtokens to each query based on its task_id; - Preserve the dtype of the p-tuning table when it is padded; - Validate that all p-tuning tables fit into max_prompt_embedding_table_size limit. Signed-off-by: Alexey Panteleev <alpanteleev@nvidia.com> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Signed-off-by: Alexey Panteleev <alpanteleev@nvidia.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Pablo Garay <palenq@gmail.com> Signed-off-by: Ao Tang <aot@nvidia.com>
rohitrango
pushed a commit
to rohitrango/NeMo
that referenced
this pull request
Jun 25, 2024
* Fixed the uses of pathlib.Path. Signed-off-by: Alexey Panteleev <alpanteleev@nvidia.com> * Add the bos token to LLAMA based models. Signed-off-by: Alexey Panteleev <alpanteleev@nvidia.com> * P-tuning related fixes: - Remember the vtoken counts for each p-tuning table when the tables are added; - Prepend the right number of vtokens to each query based on its task_id; - Preserve the dtype of the p-tuning table when it is padded; - Validate that all p-tuning tables fit into max_prompt_embedding_table_size limit. Signed-off-by: Alexey Panteleev <alpanteleev@nvidia.com> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Signed-off-by: Alexey Panteleev <alpanteleev@nvidia.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Pablo Garay <palenq@gmail.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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 ?
Fixes the implementation of PEFT for TRT-LLM export.
Collection: NLP
Changelog
PR Type:
Additional Information