feat(batch): accumulator types + batch observability (client + CLI)#1701
Draft
ebarroca wants to merge 14 commits into
Draft
feat(batch): accumulator types + batch observability (client + CLI)#1701ebarroca wants to merge 14 commits into
ebarroca wants to merge 14 commits into
Conversation
…default_view, generalized policy editor
…hema, suppressed internal type writes
Add ExecutionMode enum (direct | batch_preferred | batch_only) and execution_mode on InteractionExecutionPayload + execution_mode/batch_id on ExecutionRun, for the batch accumulator.
InferenceBatch / InferenceBatchStatus (submitted provider batch) and BatchPoolInfo (pending accumulator pool) for the batch observability endpoints.
- RunsApi.batchPools() / batches(status?) client methods. - 'vertesia batch pools' (pending pools) and 'vertesia batch list' (submitted batches) CLI commands.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
WIP — part of the batch inference accumulator (depends on llumiverse batch, vertesia/llumiverse#516).
ExecutionMode(direct | batch_preferred | batch_only) +execution_mode/batch_idon runs.InferenceBatch/InferenceBatchStatus(submitted batch) +BatchPoolInfo(pending pool) types.RunsApi.batchPools()/batches(status?)client methods.vertesia batch pools/vertesia batch listCLI.Pairs with the studio-server branch (same name). Dispatcher orchestration + /execute parking are the deploy-verified follow-up.