模型支持列表
该版本支持的模型列表如下：
3.1. 模型功能支持列表
| 表 3.1 模型功能支持列表 模型类型 | 模型名 | 量化 | 编译 | 示例包 | 备注 |
|---|---|---|---|---|---|
| classification | MobileNetV2 | ✓ | ✓ | ✓ | |
| classification | ResNet50 | ✓ | ✓ | ✓ | |
| Object Detection | YOLOv5s | ✓ | ✓ | ✓ | |
| Object Detection | YOLOv8m | ✓ | ✓ | ✓ | |
| Autonomous Driving | YOLOP | ✓ | ✓ | ✓ | |
| Object Detection | YOLOv12m | ✓ | ✓ | ✓ | |
| Pose Estimation | YOLOv8m-pose | ✓ | ✓ | ✓ | |
| Segmentation | YOLOv8m-seg | ✓ | ✓ | ✓ | |
| classification | EfficientNet | ✓ | ✓ | ✓ | |
| classification | MobileNetV3 | ✓ | ✓ | X | |
| classification | ViT-Base | ✓ | ✓ | ✓ | |
| Object Detection | YOLOv3 | ✓ | ✓ | ✓ | |
| Embedding | BGE | ✓ | ✓ | ✓ | |
| Embedding | GTE-Qwen2-1.5B | ✓ | ✓ | ✓ | |
| OCR | PP-OCRv3 | ✓ | ✓ | ✓ | |
| ASR | Whisper-medium | ✓ | ✓ | ✓ | |
| classification | YOLOv8m-cls | ✓ | ✓ | ✓ | |
| Object Detection | YOLOv11m | ✓ | ✓ | ✓ | |
| Object Detection | YOLOv10m | ✓ | ✓ | ✓ | |
| Object Detection | YOLOv5m-face | ✓ | ✓ | ✓ | |
| Object Detection | YOLOv7 | ✓ | ✓ | ✓ | |
| Object Detection | YOLOv9m | ✓ | ✓ | ✓ | |
| Object Detection | YOLOX | ✓ | ✓ | ✓ | |
| LLM | GPT-OSS-20B-A3B | ✓ | ✓ | ✓ | |
| OCR | LPRNet | ✓ | ✓ | ✓ | |
| ASR | Whisper-large-v3-turbo-0.8B | ✓ | ✓ | ✓ | |
| ASR | sensevoicesmall | ✓ | ✓ | ✓ | |
| Embedding | Qwen3-embedding-0.6B/4B/8B | ✓ | ✓ | ✓ | |
| reranker | Qwen3-reranker-0.6B/4B/8B | ✓ | ✓ | ✓ | |
| OCR | PP-OCRv5 | ✓ | ✓ | ✓ | |
| VLA | Pi0.5 | ✓ | ✓ | X | |
| ASR | FireRedASR | ✓ | ✓ | X | |
| ASR | Qwen3-ASR | ✓ | ✓ | ✓ | |
| LLM | CPM-9g-8B | ✓ | ✓ | X | |
| LLM | Qwen3.5-9B/4B/2B | ✓ | ✓ | ✓ | 9b支持MTP演示，MTP暂不支持用户量化 |
| LLM | Qwen3.5/3.6-35B-A3B | ✓ | ✓ | ✓ | |
| OCR | GLM-OCR | ✓ | ✓ | ✓ | |
| TTS | CosyVoice3-0.5B | ✓ | ✓ | ✓ | |
| VLM | Grounding-DINO | ✓ | ✓ | X | |
| ASR | GLM-ASR-Nano-2512 | ✓ | ✓ | ✓ | |
| Object Detection | YOLOv26m | ✓ | ✓ | ✓ | |
| LLM | CoPaw-Flash-9B | ✓ | ✓ | ✓ | |
| LLM | GLM4.7-flash | ✓ | ✓ | X | |
| LLM | Hunyuan-80B-A13B | ✓ | ✓ | X | |
| LLM | Kimi-VL-16B-A3B | ✓ | ✓ | X | |
| LLM | Qwen3.5/3.6-27B | ✓ | ✓ | ✓ | 支持MTP演示，MTP暂不支持用户量化 |
| MLLM | Qwen3-Omni | ✓ | ✓ | X | |
| TTS | f5-TTS | ✓ | ✓ | X | |
| VLM | Gemma4-26B-A4B | ✓ | ✓ | ✓ | |
| ASR | cam++ | ✓ | ✓ | ✓ | |
| ASR | punc_ct-transformer | ✓ | ✓ | ✓ | |
| Backbone | dinov3 | ✓ | ✓ | ✓ | |
| diffusion | z-image-turbo | ✓ | ✓ | ✓ | |
| LLM | Qwen3-next-80B-A3B | ✓ | ✓ | ✓ | |
| LLM | GPT-OSS-120B-A5B | X | X | ✓ | |
| OCR | MinerU2.5-Pro-2604-1.2B | ✓ | ✓ | ✓ | |
| TTS | Qwen3-TTS-0.6B/1.7B | ✓ | ✓ | ✓ | 1.7b预计v1.5.0支持 |
| VLM | Gemma4-e2B/e4B | ✓ | ✓ | ✓ | |
| VLM | Gemma4-31B | ✓ | ✓ | ✓ | |
| OCR | ppOCR-VL | ✓ | ✓ | X | |
| Embedding | chinese-clip | ✓ | ✓ | X |
3.2. 模型推理能力适配表
说明：
-
表中 “支持1芯”、“支持2芯”、 “支持4芯” 表示软件层面适配的算力规格，即后摩M50芯片数，而非硬件产品物理固有的芯片搭载数量。
-
✓：表示支持。 -
X：表示不支持。 -
—：表示当前版本未完成适配验证。
| 表 3.2 模型推理能力适配表 模型类型 | 模型名 | 支持1芯 | 支持2芯 | 支持4芯 | 支持多batch |
|---|---|---|---|---|---|
| classification | MobileNetV2 | ✓ | — | — | ✓ |
| classification | ResNet50 | ✓ | — | — | ✓ |
| Object Detection | YOLOv5s | ✓ | — | — | ✓ |
| Object Detection | YOLOv8m | ✓ | — | — | ✓ |
| Autonomous Driving | YOLOP | ✓ | — | — | ✓ |
| Object Detection | YOLOv12m | ✓ | — | — | ✓ |
| Pose Estimation | YOLOv8m-pose | ✓ | — | — | ✓ |
| Segmentation | YOLOv8m-seg | ✓ | — | — | ✓ |
| classification | EfficientNet | ✓ | — | — | ✓ |
| classification | MobileNetV3 | ✓ | — | — | ✓ |
| classification | ViT-Base | ✓ | — | — | ✓ |
| Object Detection | YOLOv3 | ✓ | — | — | ✓ |
| Embedding | BGE | ✓ | — | — | — |
| Embedding | GTE-Qwen2-1.5B | ✓ | — | — | — |
| OCR | PP-OCRv3 | ✓ | — | — | — |
| ASR | Whisper-medium | ✓ | — | — | — |
| classification | YOLOv8m-cls | ✓ | — | — | ✓ |
| Object Detection | YOLOv11m | ✓ | — | — | ✓ |
| Object Detection | YOLOv10m | ✓ | — | — | ✓ |
| Object Detection | YOLOv5m-face | ✓ | — | — | ✓ |
| Object Detection | YOLOv7 | ✓ | — | — | ✓ |
| Object Detection | YOLOv9m | ✓ | — | — | ✓ |
| Object Detection | YOLOX | ✓ | — | — | ✓ |
| LLM | GPT-OSS-20B-A3B | ✓ | ✓ | — | — |
| OCR | LPRNet | ✓ | — | — | — |
| ASR | Whisper-large-v3-turbo-0.8B | ✓ | — | — | — |
| ASR | sensevoicesmall | ✓ | — | — | — |
| Embedding | Qwen3-embedding-0.6B/4B/8B | ✓ | — | — | — |
| reranker | Qwen3-reranker-0.6B/4B/8B | ✓ | — | — | — |
| OCR | PP-OCRv5 | ✓ | — | — | — |
| VLA | Pi0.5 | ✓ | — | — | — |
| ASR | FireRedASR | ✓ | — | — | — |
| ASR | Qwen3-ASR | ✓ | — | — | — |
| LLM | CPM-9g-8B | ✓ | — | — | — |
| LLM | Qwen3.5-9B/4B/2B | ✓ | — | — | X |
| LLM | Qwen3.5/3.6-35B-A3B | ✓ | ✓ | — | X |
| OCR | GLM-OCR | ✓ | — | — | — |
| TTS | CosyVoice3-0.5B | ✓ | — | — | — |
| VLM | Grounding-DINO | ✓ | — | — | — |
| ASR | GLM-ASR-Nano-2512 | ✓ | — | — | — |
| Object Detection | YOLOv26m | ✓ | — | — | ✓ |
| LLM | CoPaw-Flash-9B | ✓ | — | — | — |
| LLM | GLM4.7-flash | ✓ | — | — | — |
| LLM | Hunyuan-80B-A13B | X | ✓ | — | — |
| LLM | Kimi-VL-16B-A3B | ✓ | — | — | — |
| LLM | Qwen3.5/3.6-27B | ✓ | ✓ | ✓ | X |
| MLLM | Qwen3-Omni | ✓ | — | — | — |
| TTS | f5-TTS | ✓ | — | — | — |
| VLM | Gemma4-26B-A4B | ✓ | — | — | — |
| ASR | cam++ | ✓ | — | — | — |
| ASR | punc_ct-transformer | ✓ | — | — | — |
| Backbone | dinov3 | ✓ | — | — | — |
| diffusion | z-image-turbo | ✓ | — | — | — |
| LLM | Qwen3-next-80B-A3B | X | ✓ | — | — |
| LLM | GPT-OSS-120B-A5B | X | ✓ | — | — |
| OCR | MinerU2.5-Pro-2604-1.2B | ✓ | — | — | — |
| TTS | Qwen3-TTS-0.6B/1.7B | ✓ | — | — | — |
| VLM | Gemma4-e2B/e4B | ✓ | — | — | — |
| VLM | Gemma4-31B | X | ✓ | — | — |
| OCR | ppOCR-VL | ✓ | — | — | — |
| Embedding | chinese-clip | ✓ | — | — | — |