Conversation
This commit adds the OpenAI-compatible endpoint to `dstack-proxy`, which effectively allow running services with model mappings without a gateway. Most of the OpenAI- and TGI-specific code is copied from `dstack-gateway`. This code duplication will be eliminated later, once `dstack-proxy` supports running on gateways. The commit also contains some refactoring in `dstack-proxy`: introduces `ProxyError` and `UnexpectedProxyError` exceptions and simplifies error logging in `service_proxy.py`.
jvstme
commented
Nov 4, 2024
Collaborator
Author
There was a problem hiding this comment.
Copied from dstack-gateway with minor adjustments
jvstme
commented
Nov 4, 2024
Collaborator
Author
There was a problem hiding this comment.
The next 3 files were copied from dstack-gateway with minor adjustments
Pydantic can actually work with two discriminators as long as all classes define both.
r4victor
approved these changes
Nov 5, 2024
superprat
pushed a commit
to bahaal-tech/dstack
that referenced
this pull request
Dec 20, 2024
This commit adds the OpenAI-compatible endpoint to `dstack-proxy`, which effectively allows running services with model mappings without a gateway. Most of the OpenAI- and TGI-specific code is copied from `dstack-gateway`. This code duplication will be eliminated later, once `dstack-proxy` supports running on gateways. The commit also contains some refactoring in `dstack-proxy`: introduces `ProxyError` and `UnexpectedProxyError` exceptions and simplifies error logging in `service_proxy.py`.
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This commit adds the OpenAI-compatible endpoint
to
dstack-proxy, which effectively allows runningservices with model mappings without a gateway.
Most of the OpenAI- and TGI-specific code is
copied from
dstack-gateway. This codeduplication will be eliminated later, once
dstack-proxysupports running on gateways.The commit also contains some refactoring in
dstack-proxy: introducesProxyErrorandUnexpectedProxyErrorexceptions and simplifieserror logging in
service_proxy.py.Behind the
PROXYfeature flag.Part of #1595