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>
(cherry picked from commit 08ed2b9688)
This commit is contained in:
Luciano Martins
2026-04-02 15:13:28 -03:00
committed by khluu
parent cfad6a509c
commit 8adcf8c40a
20 changed files with 5051 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
tests/models/registry.py
View File

@@ -277,6 +277,10 @@ _TEXT_GENERATION_EXAMPLE_MODELS = {
"google/gemma-2-9b", extras={"tiny": "google/gemma-2-2b-it"}
),
"Gemma3ForCausalLM": _HfExamplesInfo("google/gemma-3-1b-it"),
"Gemma4ForCausalLM": _HfExamplesInfo(
"google/gemma-4-E2B-it",
min_transformers_version="5.0.0",
),
"Gemma3nForCausalLM": _HfExamplesInfo("google/gemma-3n-E2B-it"),
"GlmForCausalLM": _HfExamplesInfo("zai-org/glm-4-9b-chat-hf"),
"Glm4ForCausalLM": _HfExamplesInfo("zai-org/GLM-4-9B-0414"),
@@ -805,6 +809,10 @@ _MULTIMODAL_EXAMPLE_MODELS = {
),
"FuyuForCausalLM": _HfExamplesInfo("adept/fuyu-8b"),
"Gemma3ForConditionalGeneration": _HfExamplesInfo("google/gemma-3-4b-it"),
"Gemma4ForConditionalGeneration": _HfExamplesInfo(
"google/gemma-4-E2B-it",
min_transformers_version="5.5.0",
),
"Gemma3nForConditionalGeneration": _HfExamplesInfo("google/gemma-3n-E2B-it"),
"GlmAsrForConditionalGeneration": _HfExamplesInfo(
"zai-org/GLM-ASR-Nano-2512",