Implement chat in BaseOpenAiGpuPredictor #1122
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
|
Just spun this into a Draft PR so it is easier for me to watch commits/comment, etc. |
elatt
commented
Sep 19, 2024
We can use this in the GPU predictor code.
This was missing from #1109
This package is breaking vLLM now (we didn't have it pinned to a version)
This support `None` better for `n`, `tempurature`, etc.
uwsgi shouldn't be needed
older versions don't have to_dict() or to_json()
|
The Needs Review labels were added based on the following file changes. Team @datarobot/core-modeling (#core-modeling) was assigned because of changes in files:custom_model_runner/datarobot_drum/drum/language_predictors/base_language_predictor.py custom_model_runner/datarobot_drum/resource/drum_server_utils.py tests/functional/run_integration_tests_in_framework_container.sh tests/functional/test_inference_per_framework.py Team @datarobot/custom-models (#custom-models) was assigned because of changes in files:custom_model_runner/datarobot_drum/drum/gpu_predictors/base.py custom_model_runner/datarobot_drum/drum/language_predictors/base_language_predictor.py custom_model_runner/datarobot_drum/resource/drum_server_utils.py public_dropin_gpu_environments/nim_llm/dr_requirements.in public_dropin_gpu_environments/nim_llm/dr_requirements.txt public_dropin_gpu_environments/vllm/Dockerfile public_dropin_gpu_environments/vllm/dr_requirements.in public_dropin_gpu_environments/vllm/dr_requirements.txt tests/functional/run_integration_tests_in_framework_container.sh tests/functional/test_inference_per_framework.py Team @datarobot/tracking-agent (#tracking-agent-reviews) was assigned because of changes in files:custom_model_runner/datarobot_drum/drum/gpu_predictors/base.py public_dropin_gpu_environments/nim_llm/dr_requirements.in public_dropin_gpu_environments/nim_llm/dr_requirements.txt public_dropin_gpu_environments/vllm/Dockerfile public_dropin_gpu_environments/vllm/dr_requirements.in public_dropin_gpu_environments/vllm/dr_requirements.txt If you think that there are some issues with ownership, please discuss with C&A domain at #core-backend-domain slack channel and create PR to update DRCODEOWNERS\CODEOWNERS file. |
baekdahl
reviewed
Oct 9, 2024
custom_model_runner/datarobot_drum/drum/language_predictors/base_language_predictor.py
Show resolved
Hide resolved
baekdahl
approved these changes
Oct 9, 2024
custom_model_runner/datarobot_drum/drum/language_predictors/base_language_predictor.py
Show resolved
Hide resolved
alexromanyuk
approved these changes
Oct 9, 2024
alexromanyuk
approved these changes
Oct 9, 2024
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.
This repository is public. Do not put here any private DataRobot or customer's data: code, datasets, model artifacts, .etc.
Summary
Update base GPU predictor to support Chat API. Also add test coverage for NIM and vLLM environments.
Rationale
The NIM and vLLM inference servers support ChatAPI natively so this adds a simple hook to pass the DRUM chat completion requests through to the backend inference servers.