Export & deploy updates (part I) #10941
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: Jan Lasek <[email protected]>
Signed-off-by: Jan Lasek <[email protected]>
Signed-off-by: Jan Lasek <[email protected]>
Signed-off-by: Jan Lasek <[email protected]>
Signed-off-by: Jan Lasek <[email protected]>
Signed-off-by: Jan Lasek <[email protected]>
Signed-off-by: Jan Lasek <[email protected]>
Signed-off-by: Jan Lasek <[email protected]>
Signed-off-by: Jan Lasek <[email protected]>
Signed-off-by: janekl <[email protected]>
![github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=60&v=4){kind=small}
| output_deployed = output_deployed["sentences"] | ||
| # MegatronLLMDeployable will return the prompt + generated output, so cut off the prompt | ||
| for i, output in enumerate(output_deployed): | ||
| output = output[len(prompts[i]) :] |
Check notice
Code scanning / CodeQL
Unused local variable Note test
There was a problem hiding this comment.
This is indeed an issue: cutting off is not really done here. Fixed in 093aa94
8 tasks
This reverts commit 8499d50. Signed-off-by: Jan Lasek <[email protected]>
Signed-off-by: Jan Lasek <[email protected]>
janekl
commented
Oct 28, 2024
| ) | ||
| return exporter | ||
| except Exception as error: | ||
| raise RuntimeError("An error has occurred during the model export. Error message: " + str(error)) |
There was a problem hiding this comment.
Suggestion: just propagate the original exception (hence removing try / catch block)
janekl
commented
Oct 28, 2024
| @@ -811,7 +808,7 @@ def str_to_bool(name: str, s: str, optional: bool = False) -> Optional[bool]: | |||
| args.test_cpp_runtime = str_to_bool("test_cpp_runtime", args.test_cpp_runtime) | |||
| args.test_deployment = str_to_bool("test_deployment", args.test_deployment) | |||
| args.functional_test = str_to_bool("functional_test", args.functional_test) | |||
| args.save_trt_engine = str_to_bool("save_trt_engin", args.save_trt_engine) | |||
| args.save_engine = str_to_bool("save_engine", args.save_engine) | |||
There was a problem hiding this comment.
Renamed as this flag is for both TRT-LLM and vLLM engines.
janekl
commented
Oct 28, 2024
| @@ -497,9 +497,6 @@ def run_existing_checkpoints( | |||
| else: | |||
| use_embedding_sharing = False | |||
|
|
|||
| if trt_llm_export_kwargs is None: | |||
| trt_llm_export_kwargs = {} | |||
Signed-off-by: Jan Lasek <[email protected]>
Signed-off-by: janekl <[email protected]>
janekl
commented
Oct 29, 2024
| @@ -591,7 +588,7 @@ def run_in_framework_inference( | |||
| output_deployed = output_deployed["sentences"] | |||
| # MegatronLLMDeployable will return the prompt + generated output, so cut off the prompt | |||
| for i, output in enumerate(output_deployed): | |||
| output = output[len(prompts[i]) :] | |||
| output_deployed[i, :] = output[0][len(prompts[i]) :] | |||
There was a problem hiding this comment.
Explained here #10941 (comment)
|
[🤖]: Hi @janekl 👋, We wanted to let you know that a CICD pipeline for this PR just finished successfully So it might be time to merge this PR or get some approvals I'm just a bot so I'll leave it you what to do next. //cc @pablo-garay @ko3n1g |
oyilmaz-nvidia
approved these changes
Oct 29, 2024
hainan-xv
pushed a commit
to hainan-xv/NeMo
that referenced
this pull request
Nov 5, 2024
* Update vLLMExporter docstring Signed-off-by: Jan Lasek <[email protected]> * No need to create empty kwargs here Signed-off-by: Jan Lasek <[email protected]> * Use debug from command line Signed-off-by: Jan Lasek <[email protected]> * Param save_engine for both both vLLM and TRT-LLM Signed-off-by: Jan Lasek <[email protected]> * Unused backend param in run_trt_llm_inference Signed-off-by: Jan Lasek <[email protected]> * Reindent files for non-existent checkpoint check Signed-off-by: Jan Lasek <[email protected]> * Docs for lora_checkpoints Signed-off-by: Jan Lasek <[email protected]> * Improve config readability Signed-off-by: Jan Lasek <[email protected]> * Raise error directly in get_vllm_deployable Signed-off-by: Jan Lasek <[email protected]> * Apply isort and black reformatting Signed-off-by: janekl <[email protected]> * Revert "Reindent files for non-existent checkpoint check" This reverts commit 8499d50. Signed-off-by: Jan Lasek <[email protected]> * Cut off prompt for real Signed-off-by: Jan Lasek <[email protected]> * Apply isort and black reformatting Signed-off-by: janekl <[email protected]> --------- Signed-off-by: Jan Lasek <[email protected]> Signed-off-by: janekl <[email protected]> Co-authored-by: janekl <[email protected]> Signed-off-by: Hainan Xu <[email protected]>
lilyw97
pushed a commit
to lilyw97/NeMo
that referenced
this pull request
Nov 13, 2024
* Update vLLMExporter docstring Signed-off-by: Jan Lasek <[email protected]> * No need to create empty kwargs here Signed-off-by: Jan Lasek <[email protected]> * Use debug from command line Signed-off-by: Jan Lasek <[email protected]> * Param save_engine for both both vLLM and TRT-LLM Signed-off-by: Jan Lasek <[email protected]> * Unused backend param in run_trt_llm_inference Signed-off-by: Jan Lasek <[email protected]> * Reindent files for non-existent checkpoint check Signed-off-by: Jan Lasek <[email protected]> * Docs for lora_checkpoints Signed-off-by: Jan Lasek <[email protected]> * Improve config readability Signed-off-by: Jan Lasek <[email protected]> * Raise error directly in get_vllm_deployable Signed-off-by: Jan Lasek <[email protected]> * Apply isort and black reformatting Signed-off-by: janekl <[email protected]> * Revert "Reindent files for non-existent checkpoint check" This reverts commit 8499d50. Signed-off-by: Jan Lasek <[email protected]> * Cut off prompt for real Signed-off-by: Jan Lasek <[email protected]> * Apply isort and black reformatting Signed-off-by: janekl <[email protected]> --------- Signed-off-by: Jan Lasek <[email protected]> Signed-off-by: janekl <[email protected]> Co-authored-by: janekl <[email protected]>
HuiyingLi
pushed a commit
to HuiyingLi/NeMo
that referenced
this pull request
Nov 15, 2024
* Update vLLMExporter docstring Signed-off-by: Jan Lasek <[email protected]> * No need to create empty kwargs here Signed-off-by: Jan Lasek <[email protected]> * Use debug from command line Signed-off-by: Jan Lasek <[email protected]> * Param save_engine for both both vLLM and TRT-LLM Signed-off-by: Jan Lasek <[email protected]> * Unused backend param in run_trt_llm_inference Signed-off-by: Jan Lasek <[email protected]> * Reindent files for non-existent checkpoint check Signed-off-by: Jan Lasek <[email protected]> * Docs for lora_checkpoints Signed-off-by: Jan Lasek <[email protected]> * Improve config readability Signed-off-by: Jan Lasek <[email protected]> * Raise error directly in get_vllm_deployable Signed-off-by: Jan Lasek <[email protected]> * Apply isort and black reformatting Signed-off-by: janekl <[email protected]> * Revert "Reindent files for non-existent checkpoint check" This reverts commit 8499d50. Signed-off-by: Jan Lasek <[email protected]> * Cut off prompt for real Signed-off-by: Jan Lasek <[email protected]> * Apply isort and black reformatting Signed-off-by: janekl <[email protected]> --------- Signed-off-by: Jan Lasek <[email protected]> Signed-off-by: janekl <[email protected]> Co-authored-by: janekl <[email protected]>
XuesongYang
pushed a commit
to paarthneekhara/NeMo
that referenced
this pull request
Jan 18, 2025
* Update vLLMExporter docstring Signed-off-by: Jan Lasek <[email protected]> * No need to create empty kwargs here Signed-off-by: Jan Lasek <[email protected]> * Use debug from command line Signed-off-by: Jan Lasek <[email protected]> * Param save_engine for both both vLLM and TRT-LLM Signed-off-by: Jan Lasek <[email protected]> * Unused backend param in run_trt_llm_inference Signed-off-by: Jan Lasek <[email protected]> * Reindent files for non-existent checkpoint check Signed-off-by: Jan Lasek <[email protected]> * Docs for lora_checkpoints Signed-off-by: Jan Lasek <[email protected]> * Improve config readability Signed-off-by: Jan Lasek <[email protected]> * Raise error directly in get_vllm_deployable Signed-off-by: Jan Lasek <[email protected]> * Apply isort and black reformatting Signed-off-by: janekl <[email protected]> * Revert "Reindent files for non-existent checkpoint check" This reverts commit 8499d50. Signed-off-by: Jan Lasek <[email protected]> * Cut off prompt for real Signed-off-by: Jan Lasek <[email protected]> * Apply isort and black reformatting Signed-off-by: janekl <[email protected]> --------- Signed-off-by: Jan Lasek <[email protected]> Signed-off-by: janekl <[email protected]> Co-authored-by: janekl <[email protected]>
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 ?
Extra changes just for cleanup purposes related to #10904, isolated here to facilitate review for main functionalities.
Collection: NLP
Changelog
Usage
# Add a code snippet demonstrating how to use thisGitHub Actions CI
The Jenkins CI system has been replaced by GitHub Actions self-hosted runners.
The GitHub Actions CI will run automatically when the "Run CICD" label is added to the PR.
To re-run CI remove and add the label again.
To run CI on an untrusted fork, a NeMo user with write access must first click "Approve and run".
Before your PR is "Ready for review"
Pre checks:
PR Type:
If you haven't finished some of the above items you can still open "Draft" PR.
Who can review?
Anyone in the community is free to review the PR once the checks have passed.
Contributor guidelines contains specific people who can review PRs to various areas.
Additional Information