biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

feat(models): implement Google Gemma 4 architecture support (MoE, Multimodal, Reasoning, Tool-Use) (#38826)

Browse Source 
Signed-off-by: Luciano Martins <lucianommartins@users.noreply.github.com>
Signed-off-by: Luciano Martins <lucianomartins@google.com>
Co-authored-by: Luciano Martins <lucianommartins@users.noreply.github.com>
Co-authored-by: Isotr0py <2037008807@qq.com>
This commit is contained in:
Luciano Martins
2026-04-02 15:13:28 -03:00
committed by GitHub
parent ecd5443dbc
commit 08ed2b9688
20 changed files with 5051 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
tests/models/multimodal/generation/test_common.py
View File

@@ -394,6 +394,22 @@ VLM_TEST_SETTINGS = {
vllm_runner_kwargs={"mm_processor_kwargs": {"do_pan_and_scan": True}},
patch_hf_runner=model_utils.gemma3_patch_hf_runner,
),
"gemma4": VLMTestInfo(
models=["google/gemma-4-E2B-it"],
test_type=(VLMTestType.IMAGE, VLMTestType.MULTI_IMAGE),
prompt_formatter=lambda img_prompt: f"<bos><start_of_turn>user\n{img_prompt}<end_of_turn>\n<start_of_turn>model\n", # noqa: E501
single_image_prompts=IMAGE_ASSETS.prompts(
{
"stop_sign": "What's the content in the center of the image?",
"cherry_blossom": "What is the season?",
}
),
multi_image_prompt="Describe the two images in detail.",
max_model_len=4096,
max_num_seqs=2,
auto_cls=AutoModelForImageTextToText,
vllm_runner_kwargs={"limit_mm_per_prompt": {"image": 4}},
),
"granite_vision": VLMTestInfo(
models=["ibm-granite/granite-vision-3.3-2b"],
test_type=(VLMTestType.IMAGE),