refactor(api): split inference and control services#21
Merged
Conversation
Signed-off-by: Connor Carpenter <connorc@nvidia.com>
|
The latest Buf updates on your PR. Results from workflow Buf / schema (pull_request).
|
Signed-off-by: Connor Carpenter <connorc@nvidia.com>
Signed-off-by: Connor Carpenter <connorc@nvidia.com>
Signed-off-by: Connor Carpenter <connorc@nvidia.com>
Signed-off-by: Connor Carpenter <connorc@nvidia.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
openengine.v1.Inferencefor generation, embedding, classification, and scoringopenengine.v1.Controlfor discovery, lifecycle, LoRA management, KV coordination, and runtime eventsengine.prototoserver.protoEngineInfoandGetEngineInfotoServerInfoandGetServerInfoServerInfo.engine_rolewhile retaining the semantically accurateEngineRoleenumParallelismInfo.decode_context_parallel_sizeWhy
The split keeps inference traffic on a small data-plane surface while coordination operations live on a separate control-plane service. Implementations can register both services on one listener or isolate
Controlby listener and access policy.Inferenceis broader and more accurate thanGeneratebecause it also owns the non-generative task RPCs. The package-qualified namesopenengine.v1.Inferenceandopenengine.v1.Controlremain concise without losing context.server.protonow matches its primaryServerInfomessage.EngineRoleremains engine-specific because aggregated, prefill, and decode describe execution roles rather than administrative server roles.Compatibility
This is an intentional pre-adoption API refinement:
/openengine.v1.Inference/*and/openengine.v1.Control/*GetEngineInfo,GetEngineInfoRequest, andEngineInfobecomeGetServerInfo,GetServerInfoRequest, andServerInfoServerInfo.rolebecomesServerInfo.engine_roleengine.protomove toserver.protodecode_context_parallel_sizeis an additive optional field; when present it must be at least one, and one means DCP is disabledValidation
protocdescriptor compilation