[VLM] Separate text-only and vision variants of the same model architecture (#13157)

docs/source/models/supported_models.md

@@ -699,10 +699,10 @@ See [this page](#generative-models) for more information on how to use generativ
   *
   * ✅︎
   * ✅︎
-- * `DeepseekVLV2ForCausalLM`
+- * `DeepseekVLV2ForCausalLM`<sup>^</sup>
   * DeepSeek-VL2
   * T + I<sup>+</sup>
-  * `deepseek-ai/deepseek-vl2-tiny`, `deepseek-ai/deepseek-vl2-small`, `deepseek-ai/deepseek-vl2` etc. (see note)
+  * `deepseek-ai/deepseek-vl2-tiny`, `deepseek-ai/deepseek-vl2-small`, `deepseek-ai/deepseek-vl2` etc.
   *
   * ✅︎
   * ✅︎
@@ -713,10 +713,10 @@ See [this page](#generative-models) for more information on how to use generativ
   *
   * ✅︎
   * ✅︎
-- * `ChatGLMModel`
+- * `GLM4VForCausalLM`<sup>^</sup>
   * GLM-4V
   * T + I
-  * `THUDM/glm-4v-9b` etc.
+  * `THUDM/glm-4v-9b`, `THUDM/cogagent-9b-20241220` etc.
   * ✅︎
   * ✅︎
   * ✅︎
@@ -825,7 +825,7 @@ See [this page](#generative-models) for more information on how to use generativ
   *
   * ✅︎
   * ✅︎
-- * `QWenLMHeadModel`
+- * `QwenVLForConditionalGeneration`<sup>^</sup>
   * Qwen-VL
   * T + I<sup>E+</sup>
   * `Qwen/Qwen-VL`, `Qwen/Qwen-VL-Chat`, etc.
@@ -862,13 +862,12 @@ See [this page](#generative-models) for more information on how to use generativ
   * ✅︎
 :::
 
+<sup>^</sup> You need to set the architecture name via `--hf-overrides` to match the one in vLLM.  
+&nbsp;&nbsp;&nbsp;&nbsp;• For example, to use DeepSeek-VL2 series models:  
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;`--hf-overrides '{"architectures": ["DeepseekVLV2ForCausalLM"]}'`  
 <sup>E</sup> Pre-computed embeddings can be inputted for this modality.  
 <sup>+</sup> Multiple items can be inputted per text prompt for this modality.
 
-:::{note}
-To use DeepSeek-VL2 series models, you have to pass `--hf_overrides '{"architectures": ["DeepseekVLV2ForCausalLM"]}'` when running vLLM.
-:::
-
 :::{note}
 H2O-VL series models will be available in V1 once we support backends other than FlashAttention.
 :::