fix(vllm): return HTTP 400 for chat completion context overflow - #3844
Open
jepio wants to merge 1 commit into
Open
fix(vllm): return HTTP 400 for chat completion context overflow#3844jepio wants to merge 1 commit into
jepio wants to merge 1 commit into
Conversation
_clamp_max_tokens raised ValueError when prompts filled max_model_len, which bypassed the chat handler and surfaced as HTTP 500. NeMo Gym then retried the deterministic request instead of treating it as overflow. Raise VLLMValidationError with a context-length message so the handler maps it to HTTP 400 that vllm_model recognizes, and add a unit test for that contract. Signed-off-by: Jeremi Piotrowski <jpiotrowski@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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What does this PR do ?
This PR fixes a contract mismatch between NeMo-RL and NeMo-Gym: when
_clamp_max_tokensdetects an overflow the ValueError exception results in an HTTP 500 error that Gym retries. Turn it into an VLLMValidationError that Gym sees as HTTP 400 and can immediately treat as a context overflow.Issues
List issues that this PR closes (syntax):
Usage
# Add a code snippet demonstrating how to use thisBefore your PR is "Ready for review"
Pre checks:
Additional Information