[Doc] Update list of supported models (#8987)

Author: DarkLight1337

docs/source/models/supported_models.rst

@@ -20,15 +20,15 @@ Decoder-only Language Models
     - Example HuggingFace Models
     - :ref:`LoRA <lora>`
   * - :code:`AquilaForCausalLM`
-    - Aquila & Aquila2
+    - Aquila, Aquila2
     - :code:`BAAI/Aquila-7B`, :code:`BAAI/AquilaChat-7B`, etc.
     - ✅︎
   * - :code:`ArcticForCausalLM`
     - Arctic
     - :code:`Snowflake/snowflake-arctic-base`, :code:`Snowflake/snowflake-arctic-instruct`, etc.
     -
   * - :code:`BaiChuanForCausalLM`
-    - Baichuan & Baichuan2
+    - Baichuan2, Baichuan
     - :code:`baichuan-inc/Baichuan2-13B-Chat`, :code:`baichuan-inc/Baichuan-7B`, etc.
     - ✅︎
   * - :code:`BloomForCausalLM`
@@ -51,6 +51,14 @@ Decoder-only Language Models
     - DeciLM
     - :code:`Deci/DeciLM-7B`, :code:`Deci/DeciLM-7B-instruct`, etc.
     -
+  * - :code:`DeepseekForCausalLM`
+    - DeepSeek
+    - :code:`deepseek-ai/deepseek-llm-67b-base`, :code:`deepseek-ai/deepseek-llm-7b-chat` etc.
+    - 
+  * - :code:`DeepseekV2ForCausalLM`
+    - DeepSeek-V2
+    - :code:`deepseek-ai/DeepSeek-V2`, :code:`deepseek-ai/DeepSeek-V2-Chat` etc.
+    - 
   * - :code:`ExaoneForCausalLM`
     - EXAONE-3
     - :code:`LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct`, etc.
@@ -83,6 +91,10 @@ Decoder-only Language Models
     - GPT-NeoX, Pythia, OpenAssistant, Dolly V2, StableLM
     - :code:`EleutherAI/gpt-neox-20b`, :code:`EleutherAI/pythia-12b`, :code:`OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5`, :code:`databricks/dolly-v2-12b`, :code:`stabilityai/stablelm-tuned-alpha-7b`, etc.
     -
+  * - :code:`GraniteForCausalLM`
+    - Granite, Power-LM
+    - :code:`ibm/granite-7b-base`, :code:`ibm/PowerLM-3b` etc.
+    - ✅︎
   * - :code:`InternLMForCausalLM`
     - InternLM
     - :code:`internlm/internlm-7b`, :code:`internlm/internlm-chat-7b`, etc.
@@ -97,7 +109,7 @@ Decoder-only Language Models
     -
   * - :code:`JambaForCausalLM`
     - Jamba
-    - :code:`ai21labs/Jamba-v0.1`, etc.
+    - :code:`ai21labs/AI21-Jamba-1.5-Large`, :code:`ai21labs/AI21-Jamba-1.5-Mini`, :code:`ai21labs/Jamba-v0.1`, etc.
     - ✅︎
   * - :code:`LlamaForCausalLM`
     - Llama 3.1, Llama 3, Llama 2, LLaMA, Yi
@@ -177,7 +189,7 @@ Decoder-only Language Models
     -
   * - :code:`StableLmForCausalLM`
     - StableLM
-    - :code:`stabilityai/stablelm-3b-4e1t/` , :code:`stabilityai/stablelm-base-alpha-7b-v2`, etc.
+    - :code:`stabilityai/stablelm-3b-4e1t`, :code:`stabilityai/stablelm-base-alpha-7b-v2`, etc.
     -
   * - :code:`Starcoder2ForCausalLM`
     - Starcoder2

vllm/model_executor/models/__init__.py

@@ -12,6 +12,7 @@
 _GENERATION_MODELS = {
     "AquilaModel": ("llama", "LlamaForCausalLM"),
     "AquilaForCausalLM": ("llama", "LlamaForCausalLM"),  # AquilaChat2
+    "ArcticForCausalLM": ("arctic", "ArcticForCausalLM"),
     "BaiChuanForCausalLM": ("baichuan", "BaiChuanForCausalLM"),  # baichuan-7b
     "BaichuanForCausalLM": ("baichuan", "BaichuanForCausalLM"),  # baichuan-13b
     "BloomForCausalLM": ("bloom", "BloomForCausalLM"),
@@ -30,9 +31,11 @@
     "GPTBigCodeForCausalLM": ("gpt_bigcode", "GPTBigCodeForCausalLM"),
     "GPTJForCausalLM": ("gpt_j", "GPTJForCausalLM"),
     "GPTNeoXForCausalLM": ("gpt_neox", "GPTNeoXForCausalLM"),
+    "GraniteForCausalLM": ("granite", "GraniteForCausalLM"),
     "InternLMForCausalLM": ("llama", "LlamaForCausalLM"),
     "InternLM2ForCausalLM": ("internlm2", "InternLM2ForCausalLM"),
     "JAISLMHeadModel": ("jais", "JAISLMHeadModel"),
+    "JambaForCausalLM": ("jamba", "JambaForCausalLM"),
     "LlamaForCausalLM": ("llama", "LlamaForCausalLM"),
     # For decapoda-research/llama-*
     "LLaMAForCausalLM": ("llama", "LlamaForCausalLM"),
@@ -52,6 +55,7 @@
     "PersimmonForCausalLM": ("persimmon", "PersimmonForCausalLM"),
     "PhiForCausalLM": ("phi", "PhiForCausalLM"),
     "Phi3ForCausalLM": ("phi3", "Phi3ForCausalLM"),
+    "Phi3SmallForCausalLM": ("phi3_small", "Phi3SmallForCausalLM"),
     "PhiMoEForCausalLM": ("phimoe", "PhiMoEForCausalLM"),
     "Qwen2ForCausalLM": ("qwen2", "Qwen2ForCausalLM"),
     "Qwen2MoeForCausalLM": ("qwen2_moe", "Qwen2MoeForCausalLM"),
@@ -62,14 +66,11 @@
     "StableLmForCausalLM": ("stablelm", "StablelmForCausalLM"),
     "Starcoder2ForCausalLM": ("starcoder2", "Starcoder2ForCausalLM"),
     "SolarForCausalLM": ("solar", "SolarForCausalLM"),
-    "ArcticForCausalLM": ("arctic", "ArcticForCausalLM"),
     "XverseForCausalLM": ("xverse", "XverseForCausalLM"),
-    "Phi3SmallForCausalLM": ("phi3_small", "Phi3SmallForCausalLM"),
+    # NOTE: The below models are for speculative decoding only
     "MedusaModel": ("medusa", "Medusa"),
     "EAGLEModel": ("eagle", "EAGLE"),
     "MLPSpeculatorPreTrainedModel": ("mlp_speculator", "MLPSpeculator"),
-    "JambaForCausalLM": ("jamba", "JambaForCausalLM"),
-    "GraniteForCausalLM": ("granite", "GraniteForCausalLM")
 }
 
 _EMBEDDING_MODELS = {