fix: vLLM health() and rerank() now honour TLS and auth credentials#5340
Open
gyliu513 wants to merge 1 commit intollamastack:mainfrom
Open
fix: vLLM health() and rerank() now honour TLS and auth credentials#5340gyliu513 wants to merge 1 commit intollamastack:mainfrom
gyliu513 wants to merge 1 commit intollamastack:mainfrom
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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?
Fix
health()andrerank()ignoring TLS/SSL and auth configuration —health()was creating a barehttpx.AsyncClient()without applyingnetwork.tlsorshared_ssl_context, causing health checks to fail against vLLM servers with self-signed certificates or enterprise CAs, andrerank()was using a bareaiohttp.ClientSession()with empty headers, failing against authenticated or custom-TLS servers.Both methods now use a shared
_build_httpx_client_kwargs()helper that mirrors the TLS resolution strategy inOpenAIMixin.client(prefernetworkconfig, fall back toshared_ssl_context),rerank()also sends theAuthorizationheader whenapi_tokenis configured,aiohttpis replaced withhttpxfor consistency with the rest of the codebase, and the redundant manualtls_verify→shared_ssl_contextlogic ininitialize()is removed since the configmodel_validatoralready migratestls_verifytonetwork.tls.verify.Test Plan