fix(CRITICAL): add --limit-mm-per-prompt image=5 — multimodal request kills engine

Engine crash: ValueError: You set image=0 (or defaulted to 1) in
--limit-mm-per-prompt, but found 1 items in the same prompt.

This kills the entire vLLM engine (AsyncEngineDeadError), making all
subsequent requests return 503. Competition sends image requests in
functional tests (d08/d09 multimodal).

Fix: --limit-mm-per-prompt image=5 allows up to 5 images per prompt.
This commit is contained in:
project6
2026-08-10 09:29:39 +00:00
parent 35f9da0c80
commit a3839dd411

View File

@@ -33,7 +33,7 @@ command:
- --dtype
- half
- --limit-mm-per-prompt
- image=1
- image=5
env:
- name: VLLM_ENGINE_ITERATION_TIMEOUT_S
value: '3600'