LlmInputs - Add ability to synthetically generate inputs #506
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
![github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=60&v=4){kind=small}
src/c++/perf_analyzer/genai-pa/genai_pa/llm_inputs/synthetic_prompt_generator.py
Fixed
Show fixed
Hide fixed
tgerdesnv
reviewed
Mar 8, 2024
src/c++/perf_analyzer/genai-pa/genai_pa/llm_inputs/llm_inputs.py
Outdated
Show resolved
Hide resolved
src/c++/perf_analyzer/genai-pa/genai_pa/llm_inputs/llm_inputs.py
Outdated
Show resolved
Hide resolved
| @@ -0,0 +1,104 @@ | |||
| The period for a new election of a citizen to | |||
There was a problem hiding this comment.
High level, this all looks great, thanks @nv-braf.
debermudez
reviewed
Mar 11, 2024
| import random | ||
| from typing import List, Tuple | ||
|
|
||
| from transformers import LlamaTokenizerFast |
There was a problem hiding this comment.
Eventually, we will add the ability to use a tokenizer from the cli but for now, we are using gpt2 in the metrics.
Can we update this one to use gpt2 as well?
There was a problem hiding this comment.
I am also okay with this being a TODO for now
debermudez
approved these changes
Mar 11, 2024
debermudez
pushed a commit
that referenced
this pull request
Mar 12, 2024
* First cut of synthetic prompt generation class * Enabled synthetic prompt generation w/ unit testing to all endpoints. * Creating a new text input for synthetic generation * Fixes based on Tim's comments * Adding GPT2 todo
debermudez
pushed a commit
that referenced
this pull request
Mar 13, 2024
* First cut of synthetic prompt generation class * Enabled synthetic prompt generation w/ unit testing to all endpoints. * Creating a new text input for synthetic generation * Fixes based on Tim's comments * Adding GPT2 todo
mc-nv
pushed a commit
that referenced
this pull request
Mar 13, 2024
* First cut of synthetic prompt generation class * Enabled synthetic prompt generation w/ unit testing to all endpoints. * Creating a new text input for synthetic generation * Fixes based on Tim's comments * Adding GPT2 todo
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.
New class to synthetically generate an input json. Have unit tests covering the new library as well as end-to-end testing to cover synthetic -> vlmm, trtllm, and both openai endpoints.