vllm-project/vllm
Vedi su GitHub[Bug]: Add tests for all parallel sampling parameter combinations
Open
#21.948 aperta il 30 lug 2025
buggood first issuekeep-openstale
Metriche repository
- Star
- (80.034 star)
- Metriche merge PR
- (Merge medio 3g 17h) (993 PR mergiate in 30 g)
Descrizione
Verify that we have tests that explicitly exercise parallel sampling (n>1 request sampling parameter) for all of the following combinations:
- Via
AsyncLLM.generate, viaLLMEngine add_request() / step() - For
output_kindequal to each ofCUMULATIVE,DELTA,FINAL_ONLY
Ideally a test for each of AsyncLLM and LLMEngine in the appropriate files, with output_kind parameterized.
Additionally we can still test LLM.generate() but this enforces FINAL_ONLY. There is already a test for this one here, but I'm not sure about the other cases.
@sethkimmel3 has reported that the LLMEngine + CUMULATIVE combination is not working properly, this should be exposed and fixed if so.