Fix: Return 'invalid_prompt' error type for invalid token IDs - #100
Open
amd-callumm wants to merge 1 commit into
Open
Fix: Return 'invalid_prompt' error type for invalid token IDs#100amd-callumm wants to merge 1 commit into
amd-callumm wants to merge 1 commit into
Conversation
RVT (ROCm Validation Tool) Spec 2.9 requires POST /v1/completions with an integer-array prompt to reject invalid token IDs with HTTP 400 and error.type "invalid_prompt". Previously, invalid token IDs correctly returned HTTP 400 but used error.type "invalid_request_error" instead of the spec-required "invalid_prompt". Changes: - Add ERROR_TYPE_INVALID_PROMPT to enum error_type (server-common.h) - Map it to "invalid_prompt" / HTTP 400 (server-common.cpp) - Use it for range + type validation errors (server-context.cpp) Invalid token types now properly rejected: - Out-of-vocabulary (t >= n_vocab) - Negative values (t < -1) - LLAMA_TOKEN_NULL (-1) without valid media chunk - Non-integer JSON types (float, string, null, boolean)
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Overview
RVT (ROCm Validation Tool) Spec 2.9 requires POST /v1/completions with an integer-array prompt to reject invalid token IDs with HTTP 400 and error.type "invalid_prompt".
Previously, invalid token IDs correctly returned HTTP 400 but used error.type "invalid_request_error" instead of the spec-required "invalid_prompt".
Additional information
Changes:
Tested with a local script (one-time; likely not worth checking in).
Invalid token types are now properly rejected:
Requirements