Supported Models

Get the latest info here: vllm-project/vllm-ascend#1608

Legend Description:

• ✅ = Supported model/feature

• ❌ = Not supported model/feature

• 🟡 = Not tested or verified

Text-Only Language Models

Generative Models

Core Supported Models

Model	Support	Note	BF16	Supported Hardware	W8A8	Chunked Prefill	Automatic Prefix Cache	LoRA	Speculative Decoding	Async Scheduling	Tensor Parallel	Pipeline Parallel	Expert Parallel	Data Parallel	Prefill-decode Disaggregation	Piecewise AclGraph	Fullgraph AclGraph	max-model-len	MLP Weight Prefetch	Doc
DeepSeek V3/3.1	✅		✅	A2/A3	✅	✅	✅		✅		✅	✅	✅	✅	✅	✅	✅	240k		DeepSeek-V3.1
DeepSeek V3.2	🔵		✅	A2/A3	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	160k	✅	DeepSeek-V3.2
DeepSeek R1	✅		✅	A2/A3	✅	✅	✅		✅		✅	✅	✅	✅	✅	✅	✅	128k		DeepSeek-R1
Qwen3	✅		✅	A2/A3	✅	✅	✅			✅	✅			✅		✅	✅	128k	✅	Qwen3-Dense
Qwen3-Coder	✅		✅	A2/A3		✅	✅	✅			✅	✅	✅	✅						Qwen3-Coder-30B-A3B tutorial
Qwen3-Moe	✅		✅	A2/A3	✅	✅	✅			✅	✅		✅	✅	✅	✅	✅	256k		Qwen3-235B-A22B
Qwen3-Next	🔵		✅	A2/A3	✅						✅			✅		✅	✅			Qwen3-Next
Qwen2.5	✅		✅	A2/A3	✅	✅	✅				✅			✅						Qwen2.5-7B
GLM-4.x	🔵			A2/A3	✅	✅	✅		✅	✅	✅			✅		✅	✅	128k		GLM-4.x
Kimi-K2-Thinking	🔵			A2/A3																Kimi-K2-Thinking

Extended Compatible Models

Model	Support	Note	Supported Hardware
DeepSeek Distill (Qwen/Llama)	✅		A2/A3
Qwen3-based	✅		A2/A3
Qwen2	✅		A2/A3
Qwen2-based	✅		A2/A3
QwQ-32B	✅		A2/A3
Llama2/3/3.1/3.2	✅		A2/A3
Internlm	🔵	#1962	A2/A3
Baichuan	🔵		A2/A3
Baichuan2	🔵		A2/A3
Phi-4-mini	🔵		A2/A3
MiniCPM	🔵		A2/A3
MiniCPM3	🔵		A2/A3
Ernie4.5	🔵		A2/A3
Ernie4.5-Moe	🔵		A2/A3
Gemma-2	🔵		A2/A3
Gemma-3	🔵		A2/A3
Phi-3/4	🔵		A2/A3
Mistral/Mistral-Instruct	🔵		A2/A3
DeepSeek V2.5	🟡	Need test
Mllama	🟡	Need test
MiniMax-Text	🟡	Need test

Pooling Models

Model	Support	Note	Supported Hardware	Doc
Qwen3-Embedding	🔵		A2/A3	Qwen3_embedding
Qwen3-VL-Embedding	🔵		A2/A3	Qwen3-VL-Embedding
Qwen3-Reranker	🔵		A2/A3	Qwen3_reranker
Qwen3-VL-Reranker	🔵		A2/A3	Qwen3-VL-Reranker
Molmo	🔵	1942	A2/A3
XLM-RoBERTa-based	🔵		A2/A3
Bert	🔵		A2/A3

Multimodal Language Models

Generative Models

Core Supported Models

Model	Support	Note	BF16	Supported Hardware	W8A8	Chunked Prefill	Automatic Prefix Cache	LoRA	Speculative Decoding	Async Scheduling	Tensor Parallel	Pipeline Parallel	Expert Parallel	Data Parallel	Prefill-decode Disaggregation	Piecewise AclGraph	Fullgraph AclGraph	max-model-len	MLP Weight Prefetch	Doc
Qwen2.5-VL	✅		✅	A2/A3	✅	✅	✅			✅	✅				✅	✅	✅	30k		Qwen-VL-Dense
Qwen3-VL	✅			A2/A3							✅					✅	✅			Qwen-VL-Dense
Qwen3-VL-MOE	✅		✅	A2/A3		✅	✅			✅	✅	✅	✅	✅	✅	✅	✅	256k		Qwen3-VL-MOE
Qwen3-Omni-30B-A3B-Thinking	🔵			A2/A3							✅		✅							Qwen3-Omni-30B-A3B-Thinking
Qwen2.5-Omni	🔵			A2/A3																Qwen2.5-Omni

Extended Compatible Models

Model	Support	Note	Supported Hardware
Qwen2-VL	✅		A2/A3
Qwen3-Omni	🔵		A2/A3
QVQ	🔵		A2/A3
Qwen2-Audio	🔵		A2/A3
Aria	🔵		A2/A3
LLaVA-Next	🔵		A2/A3
LLaVA-Next-Video	🔵		A2/A3
MiniCPM-V	🔵		A2/A3
Mistral3	🔵		A2/A3
Phi-3-Vision/Phi-3.5-Vision	🔵		A2/A3
Gemma3	🔵		A2/A3
Llama3.2	🔵		A2/A3
PaddleOCR-VL	🔵		A2/A3
Llama4	❌	1972
Keye-VL-8B-Preview	❌	1963
Florence-2	❌	2259
GLM-4V	❌	2260
InternVL2.0/2.5/3.0 InternVideo2.5/Mono-InternVL	❌	2064
Whisper	❌	2262
Ultravox	🟡	Need test