Supported Models

Supported Models#

Model

Supported

Note

DeepSeek v3

DeepSeek R1

DeepSeek Distill (Qwen/LLama)

Qwen2-VL

Qwen2-Audio

Qwen2.5

Qwen2.5-VL

QwQ-32B

MiniCPM

LLama3.1/3.2

Mistral

Need test

DeepSeek v2.5

Need test

Gemma-2

Need test

Baichuan

Need test

Internlm

ChatGLM

Plan in Q2

InternVL2.5

GLM-4v

Need test

Molomo

LLaVA1.5

LLaVA 1.6

Modify the default value of max_position_embeddings in the weight file config.json to 5120 to run LLaVA 1.6 on Ascend NPU

Mllama

Need test

LLaVA-Next

Need test

LLaVA-Next-Video

Need test

Phi-3-Vison/Phi-3.5-Vison

Need test

Ultravox

Need test