[Bug]: Unrecognized configuration class when running TriMix example code on Qwen-2.5-VL model

Describe the bug

ValueError: Unrecognized configuration class <class 'transformers.models.qwen2_5_vl.configuration_qwen2_5_vl.Qwen2_5_VLConfig'> for this kind of AutoModel: AutoModelForCausalLM.
Model type should be one of ApertusConfig, ArceeConfig, AriaTextConfig, BambaConfig, BartConfig, BertConfig, BertGenerationConfig, BigBirdConfig, BigBirdPegasusConfig, BioGptConfig, BitNetConfig, BlenderbotConfig, BlenderbotSmallConfig, BloomConfig, BltConfig, CamembertConfig, LlamaConfig, CodeGenConfig, CohereConfig, Cohere2Config, CpmAntConfig, CTRLConfig, Data2VecTextConfig, DbrxConfig, DeepseekV2Config, DeepseekV3Config, DiffLlamaConfig, DogeConfig, Dots1Config, ElectraConfig, Emu3Config, ErnieConfig, Ernie4_5Config, Ernie4_5_MoeConfig, Exaone4Config, FalconConfig, FalconH1Config, FalconMambaConfig, FlexOlmoConfig, FuyuConfig, GemmaConfig, Gemma2Config, Gemma3Config, Gemma3TextConfig, Gemma3nConfig, Gemma3nTextConfig, GitConfig, GlmConfig, Glm4Config, Glm4MoeConfig, GotOcr2Config, GPT2Config, GPT2Config, GPTBigCodeConfig, GPTNeoConfig, GPTNeoXConfig, GPTNeoXJapaneseConfig, GptOssConfig, GPTJConfig, GraniteConfig, GraniteMoeConfig, GraniteMoeHybridConfig, GraniteMoeSharedConfig, HeliumConfig, HunYuanDenseV1Config, HunYuanMoEV1Config, JambaConfig, JetMoeConfig, Lfm2Config, LlamaConfig, Llama4Config, Llama4TextConfig, LongcatFlashConfig, MambaConfig, Mamba2Config, MarianConfig, MBartConfig, MegaConfig, MegatronBertConfig, MiniMaxConfig, MinistralConfig, MistralConfig, MixtralConfig, MllamaConfig, ModernBertDecoderConfig, MoshiConfig, MptConfig, MusicgenConfig, MusicgenMelodyConfig, MvpConfig, NemotronConfig, OlmoConfig, Olmo2Config, Olmo3Config, OlmoeConfig, OpenLlamaConfig, OpenAIGPTConfig, OPTConfig, PegasusConfig, PersimmonConfig, PhiConfig, Phi3Config, Phi4MultimodalConfig, PhimoeConfig, PLBartConfig, ProphetNetConfig, QDQBertConfig, Qwen2Config, Qwen2MoeConfig, Qwen3Config, Qwen3MoeConfig, Qwen3NextConfig, RecurrentGemmaConfig, ReformerConfig, RemBertConfig, RobertaConfig, RobertaPreLayerNormConfig, RoCBertConfig, RoFormerConfig, RwkvConfig, SeedOssConfig, SmolLM3Config, Speech2Text2Config, StableLmConfig, Starcoder2Config, TransfoXLConfig, TrOCRConfig, VaultGemmaConfig, WhisperConfig, XGLMConfig, XLMConfig, XLMProphetNetConfig, XLMRobertaConfig, XLMRobertaXLConfig, XLNetConfig, xLSTMConfig, XmodConfig, ZambaConfig, Zamba2Config.

Steps to reproduce

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from minference import MInference

model_name = "/path/to/model/Qwen2.5-VL-7B-Instruct"

tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=False)
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype=torch.bfloat16,
device_map="auto",
trust_remote_code=False,
attn_implementation="flash_attention_2",
)

minference_patch = MInference(
attn_type="tri_mix",
model_name=model_name,
attn_kwargs={"last_n": 128, "starting_layer": 16, "n_local": 512, "n_init": 8},
)
model = minference_patch(model)

prompt = "your prompt here"
inputs = tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device)
output = model.generate(**inputs, do_sample=False, max_new_tokens=50)

Expected Behavior

No response

Logs

No response

Additional Information

MInference==0.1.6.0
python==3.12.7
torch==2.8.0
vllm==0.10.2

Start by reproducing the TriMix example with MInference 0.1.6.0, the Qwen2.5-VL-7B-Instruct model, and the shown AutoModelForCausalLM loading call. Inspect the MInference entry point and TriMix integration to determine the supported model class; done means the example loads, applies the patch, and generates output without the configuration-class error.