docs: align engine and provider lists with the shipped gateway - #33
Merged
Conversation
Homepage 'How it works' cards: gRPC workers now list all five engines (vLLM, SGLang, TokenSpeed, TRT-LLM, MLX); HTTP workers list the two engines detectable over HTTP plus the OpenAI-compatible path; External APIs mirror the gateway README diagram (OCI after Gemini, Bedrock dropped from the card). Architecture overview provider table: AWS Bedrock and OCI Generative AI are reached through their OpenAI-compatible modes, not dedicated API styles — the gateway's dedicated adapters are OpenAI, Anthropic, Gemini, and xAI. Signed-off-by: Simo Lin <25425177+slin1237@users.noreply.github.com>
slin1237
force-pushed
the
docs/align-backends-with-gateway
branch
from
August 2, 2026 06:14
50f1051 to
0aaf1f4
Compare
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Counterpart to smg-project/smg#2030 — the site carried the same drift the gateway README had.
Changes
Homepage "How it works" cards (
HomeHowItWorks.svelte):SGLang / vLLM / TRT-LLM→ all five engines:vLLM / SGLang / TokenSpeed+TRT-LLM / MLXSGLang / vLLM / TRT-LLM→vLLM / SGLang(the engines the gateway can identify over HTTP) +OpenAI-CompatibleGroq / Together / Bedrock→OCI / Groq / Together, matching the gateway README's architecture diagram (OCI placed after Gemini)Architecture overview (
concepts/architecture/overview.md): the Supported Providers table listedBedrockandOCIas dedicated API styles — no such adapters exist in the gateway (ProviderTypecovers OpenAI, xAI, Anthropic, Gemini + custom). Both rows now sayOpenAI-compatible, which is the real path (their OpenAI-compat modes through the passthrough).Not in this PR, flagged for follow-up:
concepts/routing/load-balancing.mddocuments 8 policies — the gateway ships 10 (least_loadandpassthroughare missing and deserve real writeups, not a count bump).Verification
pnpm check: 694 files, 0 errors (1 pre-existing warning inHeroMark.svelte, untouched)