Fix LiteLLM split iteration in greedy_until to avoid duplicate API requests#1177
Open
dyurchenko98 wants to merge 1 commit intohuggingface:mainfrom
Open
Fix LiteLLM split iteration in greedy_until to avoid duplicate API requests#1177dyurchenko98 wants to merge 1 commit intohuggingface:mainfrom
dyurchenko98 wants to merge 1 commit intohuggingface: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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
This PR fixes a regression in
LiteLLMClient.greedy_untilwhere contexts were built from the full dataset inside the split loop, instead of the current split.Root Cause
In the split loop in
litellm_model.py, this line used full-dataset iteration:contexts = [self.prompt_manager.prepare_prompt_api(doc) for doc in dataset]Because of that, for
Ssplits andNdocs, LiteLLM sent ~N*Srequests instead ofN.Changes
Updated split loop context construction to use split-local docs:
contexts = [self.prompt_manager.prepare_prompt_api(doc) for doc in split]Added regression test:
tests/unit/models/endpoints/test_litellm_split_iteration.py
Verifies API call inputs are split-local and total sent requests equals total docs (no redundant requests).
Why this matters
Prevents redundant API calls and extra cost.
Ensures split-level params (
generation_size,use_logits,num_samples,stop_sequences) are applied to the correct group.Prevents silently dropped extra responses after
get_original_order.