diff --git a/docs/models/supported_models.md b/docs/models/supported_models.md index ea36331542..a24fa4bcce 100644 --- a/docs/models/supported_models.md +++ b/docs/models/supported_models.md @@ -409,6 +409,12 @@ th { | `MiniMaxText01ForCausalLM` | MiniMax-Text | `MiniMaxAI/MiniMax-Text-01`, etc. | | | ✅︎ | | `Zamba2ForCausalLM` | Zamba2 | `Zyphra/Zamba2-7B-instruct`, `Zyphra/Zamba2-2.7B-instruct`, `Zyphra/Zamba2-1.2B-instruct`, etc. | | | ✅︎ | +Some models are supported only via the [Transformers backend](#transformers). The purpose of the table below is to acknowledge models which we officially support in this way. The logs will say that the Transformers backend is being used, and you will see no warning that this is fallback behaviour. This means that, if you have issues with any of the models listed below, please [make an issue](https://github.com/vllm-project/vllm/issues/new/choose) and we'll do our best to fix it! + +| Architecture | Models | Example HF Models | [LoRA](../features/lora.md) | [PP](../serving/parallelism_scaling.md) | [V1](gh-issue:8779) | +|--------------|--------|-------------------|----------------------|---------------------------|---------------------| +| `SmolLM3ForCausalLM` | SmolLM3 | `HuggingFaceTB/SmolLM3-3B` | ✅︎ | ✅︎ | ✅︎ | + !!! note Currently, the ROCm version of vLLM supports Mistral and Mixtral only for context lengths up to 4096. diff --git a/tests/models/registry.py b/tests/models/registry.py index eae5829030..d7d20d1f3a 100644 --- a/tests/models/registry.py +++ b/tests/models/registry.py @@ -291,6 +291,7 @@ _TEXT_GENERATION_EXAMPLE_MODELS = { "Qwen3ForCausalLM": _HfExamplesInfo("Qwen/Qwen3-8B"), "Qwen3MoeForCausalLM": _HfExamplesInfo("Qwen/Qwen3-30B-A3B"), "RWForCausalLM": _HfExamplesInfo("tiiuae/falcon-40b"), + "SmolLM3ForCausalLM": _HfExamplesInfo("HuggingFaceTB/SmolLM3-3B"), "StableLMEpochForCausalLM": _HfExamplesInfo("stabilityai/stablelm-zephyr-3b"), # noqa: E501 "StableLmForCausalLM": _HfExamplesInfo("stabilityai/stablelm-3b-4e1t"), "Starcoder2ForCausalLM": _HfExamplesInfo("bigcode/starcoder2-3b"), diff --git a/vllm/model_executor/models/registry.py b/vllm/model_executor/models/registry.py index 279e045a70..64dbde4916 100644 --- a/vllm/model_executor/models/registry.py +++ b/vllm/model_executor/models/registry.py @@ -271,6 +271,9 @@ _SPECULATIVE_DECODING_MODELS = { } _TRANSFORMERS_SUPPORTED_MODELS = { + # Text generation models + "SmolLM3ForCausalLM": ("transformers", "TransformersForCausalLM"), + # Multimodal models "Emu3ForConditionalGeneration": ("transformers", "TransformersForMultimodalLM"), # noqa: E501 }