Export & deploy updates (part II) #11344
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 <janek.lasek@gmail.com>
Signed-off-by: Jan Lasek <janek.lasek@gmail.com>
Signed-off-by: Jan Lasek <janek.lasek@gmail.com>
Signed-off-by: Jan Lasek <janek.lasek@gmail.com>
Signed-off-by: Jan Lasek <janek.lasek@gmail.com>
Signed-off-by: Jan Lasek <janek.lasek@gmail.com>
Signed-off-by: Jan Lasek <janek.lasek@gmail.com>
|
beep boop 🤖: 🙏 The following files have warnings. In case you are familiar with these, please try helping us to improve the code base. Your code was analyzed with PyLint. The following annotations have been identified: Thank you for improving NeMo's documentation! |
|
[🤖]: 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 |
Signed-off-by: Jan Lasek <janek.lasek@gmail.com>
Signed-off-by: Jan Lasek <janek.lasek@gmail.com>
janekl
force-pushed
the
jlasek/export_deploy_part_2
branch
from
cb06125 to
197b235
Compare
Signed-off-by: Jan Lasek <janek.lasek@gmail.com>
Signed-off-by: Jan Lasek <janek.lasek@gmail.com>
janekl
commented
Nov 21, 2024
| @@ -5,7 +5,7 @@ diffusers>=0.19.3 | |||
| einops_exts | |||
| imageio | |||
| kornia | |||
| megatron-energon | |||
| megatron-energon<3.0.0 | |||
|
[🤖]: 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 |
XuesongYang
pushed a commit
to paarthneekhara/NeMo
that referenced
this pull request
Jan 18, 2025
* Set debug level accordingly and use logger for some prints Signed-off-by: Jan Lasek <janek.lasek@gmail.com> * Param model_type is in fact required for vLLM deployment Signed-off-by: Jan Lasek <janek.lasek@gmail.com> * It's time to remove version check Signed-off-by: Jan Lasek <janek.lasek@gmail.com> * Start using v2 block manager (default) in vLLM Signed-off-by: Jan Lasek <janek.lasek@gmail.com> * Rename original NeMo SP tokenizer to solve UnboundLocalError Signed-off-by: Jan Lasek <janek.lasek@gmail.com> * Add output_generation_logits as Triton input for vLLM exporter Signed-off-by: Jan Lasek <janek.lasek@gmail.com> * Update requirements_vllm.txt Signed-off-by: Jan Lasek <janek.lasek@gmail.com> * Refer to NeMo tokenizers explicitely Signed-off-by: Jan Lasek <janek.lasek@gmail.com> --------- Signed-off-by: Jan Lasek <janek.lasek@gmail.com>
youngeunkwon0405
pushed a commit
to youngeunkwon0405/NeMo
that referenced
this pull request
Feb 10, 2025
* Set debug level accordingly and use logger for some prints Signed-off-by: Jan Lasek <janek.lasek@gmail.com> * Param model_type is in fact required for vLLM deployment Signed-off-by: Jan Lasek <janek.lasek@gmail.com> * It's time to remove version check Signed-off-by: Jan Lasek <janek.lasek@gmail.com> * Start using v2 block manager (default) in vLLM Signed-off-by: Jan Lasek <janek.lasek@gmail.com> * Rename original NeMo SP tokenizer to solve UnboundLocalError Signed-off-by: Jan Lasek <janek.lasek@gmail.com> * Add output_generation_logits as Triton input for vLLM exporter Signed-off-by: Jan Lasek <janek.lasek@gmail.com> * Update requirements_vllm.txt Signed-off-by: Jan Lasek <janek.lasek@gmail.com> * Refer to NeMo tokenizers explicitely Signed-off-by: Jan Lasek <janek.lasek@gmail.com> --------- Signed-off-by: Jan Lasek <janek.lasek@gmail.com> Signed-off-by: Youngeun Kwon <youngeunk@nvidia.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 ?
Several updates & bugfixes for
nemo.exportmodule.UnboundLocalErrorwhen building tokenizer innemo/export/trt_llm/nemo_ckpt_loader/nemo_file.pyoutput_generation_logits(disabled in case of vLLM for now)BlockManagerV2by default for vLLM deployment (asV1is getting deprecated)/opt/venvin the dedicated filerequirements_vllm.txt.Collection: NLP / LLM
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