Optimum RBLN¶
Optimum RBLN serves as a bridge connecting the HuggingFace transformers/diffusers libraries to RBLN NPUs, i.e. ATOM™ (RBLN-CA02), ATOM™+ (RBLN-CA12 and RBLN-CA22), and ATOM™-Max (RBLN-CA25). It offers a set of tools that enable easy model compilation and inference for both single and multi-NPU (Rebellions Scalable Design) configurations across a range of downstream tasks. The following table presents the comprehensive lineup of models currently supported by Optimum RBLN.
Transformers¶
Single NPU¶
| Model | Model Architecture | Task |
|---|---|---|
| Phi-2 | PhiForCausalLM | |
| Gemma-2b | GemmaForCausalLM | |
| OPT-2.7b | OPTForCausalLM | |
| GPT2 | GPT2LMHeadModel | |
| GPT2-medium | GPT2LMHeadModel | |
| GPT2-large | GPT2LMHeadModel | |
| GPT2-xl | GPT2LMHeadModel | |
| T5-small | T5ForConditionalGeneration | |
| T5-base | T5ForConditionalGeneration | |
| T5-large | T5ForConditionalGeneration | |
| T5-3b | T5ForConditionalGeneration | |
| BART-base | BartForConditionalGeneration | |
| BART-large | BartForConditionalGeneration | |
| KoBART-base | BartForConditionalGeneration | |
| E5-base-4K | BertModel | |
| LaBSE | BertModel | |
| KR-SBERT-V40K-klueNLI-augSTS | BertModel | |
| BERT-base | - BertForMaskedLM - BertForQuestionAnswering |
|
| BERT-large | - BertForMaskedLM - BertForQuestionAnswering |
|
| DistilBERT-base | DistilBertForQuestionAnswering | |
| SecureBERT | RobertaForMaskedLM | |
| RoBERTa | RobertaForSequenceClassification | |
| BGE-Small-EN-v1.5 | RBLNBertModel | |
| BGE-Base-EN-v1.5 | RBLNBertModel | |
| BGE-Large-EN-v1.5 | RBLNBertModel | |
| BGE-M3 | XLMRobertaModel | |
| BGE-Reranker-V2-M3 | XLMRobertaForSequenceClassification | |
| BGE-Reranker-Base | XLMRobertaForSequenceClassification | |
| BGE-Reranker-Large | XLMRobertaForSequenceClassification | |
| Ko-Reranker | XLMRobertaForSequenceClassification | |
| Time-Series-Transformer | TimeSeriesTransformerForPrediction | |
| BLIP2-2.7b | RBLNBlip2ForConditionalGeneration | |
| Whisper-tiny | WhisperForConditionalGeneration | |
| Whisper-base | WhisperForConditionalGeneration | |
| Whisper-small | WhisperForConditionalGeneration | |
| Whisper-medium | WhisperForConditionalGeneration | |
| Whisper-large-v3 | WhisperForConditionalGeneration | |
| Whisper-large-v3-turbo | WhisperForConditionalGeneration | |
| Wav2Vec2 | Wav2Vec2ForCTC | |
| Audio-Spectogram-Transformer | ASTForAudioClassification | |
| DPT-large | DPTForDepthEstimation | |
| ViT-large | ViTForImageClassification | |
| ResNet50 | ResNetForImageClassification |
Multi-NPU (RSD)¶
Note
Rebellions Scalable Design (RSD) is available on ATOM™+ (RBLN-CA12 and RBLN-CA22) and ATOM™-Max (RBLN-CA25). You can check the type of your current RBLN NPU using the rbln-stat command.
| Model | Model Architecture | Recommended # of NPUs | Task |
|---|---|---|---|
| DeepSeek-R1-Distill-Llama-8b | LlamaForCausalLM | 8 | |
| DeepSeek-R1-Distill-Llama-70b | LlamaForCausalLM | 16 | |
| DeepSeek-R1-Distill-Qwen-1.5b | Qwen2ForCausalLM | 8 | |
| DeepSeek-R1-Distill-Qwen-7b | Qwen2ForCausalLM | 8 | |
| DeepSeek-R1-Distill-Qwen-14b | Qwen2ForCausalLM | 8 | |
| DeepSeek-R1-Distill-Qwen-32b | Qwen2ForCausalLM | 16 | |
| Llama3.3-70b | LlamaForCausalLM | 16 | |
| Llama3.2-3b | LlamaForCausalLM | 8 | |
| Llama3.1-70b | LlamaForCausalLM | 16 | |
| Llama3.1-8b | LlamaForCausalLM | 8 | |
| Llama3-8b | LlamaForCausalLM | 4 or 8 | |
| Llama3-8b + LoRA | LlamaForCausalLM | 4 or 8 | |
| Llama2-7b | LlamaForCausalLM | 4 or 8 | |
| Llama2-13b | LlamaForCausalLM | 4 or 8 | |
| Gemma-7b | GemmaForCausalLM | 4 or 8 | |
| Mistral-7b | MistralForCausalLM | 4 or 8 | |
| Qwen2-7b | Qwen2ForCausalLM | 4 or 8 | |
| Qwen2.5-7b | Qwen2ForCausalLM | 4 or 8 | |
| Qwen2.5-14b | Qwen2ForCausalLM | 4 or 8 | |
| OPT-6.7b | OPTForCausalLM | 4 | |
| Salamandra-7b | LlamaForCausalLM | 4 or 8 | |
| KONI-Llama3.1-8b | LlamaForCausalLM | 8 | |
| EXAONE-3.0-7.8b | ExaoneForCausalLM | 4 or 8 | |
| EXAONE-3.5-2.4b | ExaoneForCausalLM | 4 | |
| EXAONE-3.5-7.8b | ExaoneForCausalLM | 4 or 8 | |
| EXAONE-3.5-32b | ExaoneForCausalLM | 8 or 16 | |
| Mi:dm-7b | MidmLMHeadModel | 4 or 8 | |
| SOLAR-10.7b | LlamaForCausalLM | 4 or 8 | |
| EEVE-Korean-10.8b | LlamaForCausalLM | 4 or 8 | |
| T5-11b | T5ForConditionalGeneration | 2 or 4 | |
| T5-Enc-11b | T5EncoderModel | 2 or 4 | |
| Gemma3-27b | Gemma3ForConditionalGeneration | 16 | |
| Qwen2.5-VL-7b | Qwen2_5_VLForConditionalGeneration | 8 | |
| Idefics3-8B-Llama3 | Idefics3ForConditionalGeneration | 8 | |
| Llava-v1.6-mistral-7b | LlavaNextForConditionalGeneration | 4 or 8 | |
| BLIP2-6.7b | RBLNBlip2ForConditionalGeneration | 4 |
Diffusers¶
Note
Models marked with a superscript, †, require more than one ATOM™ due to their large weight size exceeding the capacity of a single ATOM™. This necessitates dividing the model's modules across multiple ATOM™s. For detailed information regarding the specific module distribution, please refer to the model code.
| Model | Model Architecture | Task |
|---|---|---|
| Stable Diffusion |
|
|
| Stable Diffusion + LoRA |
|
|
| Stable Diffusion V3† |
|
|
| Stable Diffusion XL |
|
|
| Stable Diffusion XL + multi-LoRA |
|
|
| SDXL-turbo |
|
|
| Stable Diffusion + ControlNet |
|
|
| Stable Diffusion XL + ControlNet |
|
|
| Kandinsky V2.2 |
|