[TEST]Update mm param --mm-processor-cache-gb (#5242)

### What this PR does / why we need it?
This PR updates the mm param --mm-processor-cache-gb, we need it to run
the case

### Does this PR introduce _any_ user-facing change?
No

### How was this patch tested?
by running the test

- vLLM version: release/v0.13.0
- vLLM main:
ad32e3e19c

Signed-off-by: jiangyunfan1 <jiangyunfan1@h-partners.com>
This commit is contained in:
jiangyunfan1
2025-12-22 18:54:03 +08:00
committed by GitHub
parent 61efaffcaf
commit 3ba920a65b
2 changed files with 2 additions and 2 deletions

View File

@@ -80,7 +80,7 @@ async def test_models(model: str, tp_size: int) -> None:
"HCCL_OP_EXPANSION_MODE": "AIV"
}
server_args = [
"--no-enable-prefix-caching", "--disable-mm-preprocessor-cache",
"--no-enable-prefix-caching", "--mm-processor-cache-gb", "0",
"--tensor-parallel-size",
str(tp_size), "--port",
str(port), "--max-model-len", "30000", "--max-num-batched-tokens",

View File

@@ -72,7 +72,7 @@ async def test_models(model: str, tp_size: int) -> None:
"HCCL_OP_EXPANSION_MODE": "AIV"
}
server_args = [
"--no-enable-prefix-caching", "--disable-mm-preprocessor-cache",
"--no-enable-prefix-caching", "--mm-processor-cache-gb", "0",
"--tensor-parallel-size",
str(tp_size), "--port",
str(port), "--max-model-len", "30000", "--max-num-batched-tokens",