Generalize ChatQnA external LLM to external inferencing support #1167
Conversation
This file contains hidden or 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
2 tasks
eero-t
changed the title
eero-t
force-pushed
the
external-inferencing
branch
from
30ae64a to
4742ac4
Compare
Signed-off-by: Eero Tamminen <[email protected]>
eero-t
force-pushed
the
external-inferencing
branch
from
2a50e5d to
09c57c6
Compare
Collaborator
|
This PR is stale because it has been open 30 days with no activity. Remove stale label or comment or this will be closed in 7 days. |
Collaborator
|
This PR was closed because it has been stalled for 7 days with no activity. |
Collaborator
Author
|
KubeAI just got support for LLM It's not in any release yet though. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
Description
vLLM already support all ChatQnA inferencing sub-services: LLM, embedding, reranking, guardrails. In ChatQnA example value files, all except embedding are HW accelerated. Additionally, KubeAI already supports first three, and OPEA has Enterprise-Inferencing subproject: https://github.com/opea-project/Enterprise-Inference
Therefore it seems relevant to start discussion on how current external LLM support in the Helm charts could be changed to a more generic external inferencing support, before current support gets into too wide use.
To start that discussing, this PR includes draft of such changes for ChatQnA, and TODOs for items currently missing from ChatQnA code in GenAIExamples.
Issues
n/a.Type of change
Dependencies
This is dependency disconnection.
Tests
Not relevant yet.