Track TPD and RPM for all providers, not just Groq - #38
Merged
Conversation
MODEL_LIMITS flattens MODEL_REGISTRY into a single per-model RPM/RPD/TPM/TPD lookup, replacing the Groq-only MODEL_TPD_LIMITS dict. Cerebras and Mistral cap usage at the account level, so their models now share a scope_key and pool daily call/token usage correctly instead of tracking each model id independently. Added a sliding 60s RPM window (_wait_for_rpm) to catch account-wide RPM bursts that static per-call pacing alone would miss.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
MODEL_LIMITS flattens MODEL_REGISTRY into a single per-model RPM/RPD/TPM/TPD lookup, replacing the Groq-only MODEL_TPD_LIMITS dict. Cerebras and Mistral cap usage at the account level, so their models now share a scope_key and pool daily call/token usage correctly instead of tracking each model id independently. Added a sliding 60s RPM window (_wait_for_rpm) to catch account-wide RPM bursts that static per-call pacing alone would miss.