A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 14, 05:30 UTC
[Docs] remove v1 column for embedding models (#27446)
Signed-off-by: piood <2477084691@qq.com> Signed-off-by: Cyrus Leung <cyrus.tl.leung@gmail.com> Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Yu Jiaqi committed
Oct 24, 2025 at 14:55 UTC
88d3141ec63008d8dff63311359355ebbe98ad64
1 file changed
+7
-7
docs/models/supported_models.md
+7
-7
@@ -800,13 +800,13 @@ These models primarily support the [`LLM.embed`](./pooling_models.md#llmembed) A
800
801
The following table lists those that are tested in vLLM.
802
803
-| Architecture | Models | Inputs | Example HF Models | [LoRA](../features/lora.md) | [PP](../serving/parallelism_scaling.md) | [V1](gh-issue:8779) |
804
-|--------------|--------|--------|-------------------|----------------------|---------------------------|---------------------|
805
-| `CLIPModel` | CLIP | T / I | `openai/clip-vit-base-patch32`, `openai/clip-vit-large-patch14`, etc. | | | ✅︎ |
806
-| `LlavaNextForConditionalGeneration`<sup>C</sup> | LLaVA-NeXT-based | T / I | `royokong/e5-v` | | ✅︎ | ✅︎ |
807
-| `Phi3VForCausalLM`<sup>C</sup> | Phi-3-Vision-based | T + I | `TIGER-Lab/VLM2Vec-Full` | | ✅︎ | ✅︎ |
808
-| `SiglipModel` | SigLIP | T / I | `google/siglip-base-patch16-224` | | | ✅︎ |
809
-| `*ForConditionalGeneration`<sup>C</sup>, `*ForCausalLM`<sup>C</sup>, etc. | Generative models | \* | N/A | \* | \* | \* |
803
+| Architecture | Models | Inputs | Example HF Models | [LoRA](../features/lora.md) | [PP](../serving/parallelism_scaling.md) |
804
+|--------------|--------|--------|-------------------|----------------------|---------------------------|
805
+| `CLIPModel` | CLIP | T / I | `openai/clip-vit-base-patch32`, `openai/clip-vit-large-patch14`, etc. | | |
806
+| `LlavaNextForConditionalGeneration`<sup>C</sup> | LLaVA-NeXT-based | T / I | `royokong/e5-v` | | ✅︎ |
807
+| `Phi3VForCausalLM`<sup>C</sup> | Phi-3-Vision-based | T + I | `TIGER-Lab/VLM2Vec-Full` | | ✅︎ |
808
+| `SiglipModel` | SigLIP | T / I | `google/siglip-base-patch16-224` | | |
809
+| `*ForConditionalGeneration`<sup>C</sup>, `*ForCausalLM`<sup>C</sup>, etc. | Generative models | \* | N/A | \* | \* |
810
811
<sup>C</sup> Automatically converted into an embedding model via `--convert embed`. ([details](./pooling_models.md#model-conversion))
812
\* Feature support is the same as that of the original model.