[Model] Add OLMoE (vllm-project#7922)

MengqingCao · Sep 30, 2024 · df42c97 · df42c97
1 parent a642d84
commit df42c97
Show file tree

Hide file tree

Showing 3 changed files with 414 additions and 0 deletions.
diff --git a/docs/source/models/supported_models.rst b/docs/source/models/supported_models.rst
@@ -127,6 +127,10 @@ Decoder-only Language Models
     - Nemotron-3, Nemotron-4, Minitron
     - :code:`nvidia/Minitron-8B-Base`, :code:`mgoin/Nemotron-4-340B-Base-hf-FP8`, etc.
     - ✅︎
+  * - :code:`OLMoEForCausalLM`
+    - OLMoE
+    - :code:`allenai/OLMoE-1B-7B-0924`, :code:`allenai/OLMoE-1B-7B-0924-Instruct`, etc.
+    -
   * - :code:`OLMoForCausalLM`
     - OLMo
     - :code:`allenai/OLMo-1B-hf`, :code:`allenai/OLMo-7B-hf`, etc.

diff --git a/vllm/model_executor/models/__init__.py b/vllm/model_executor/models/__init__.py
@@ -46,6 +46,7 @@
     "MiniCPM3ForCausalLM": ("minicpm3", "MiniCPM3ForCausalLM"),
     "NemotronForCausalLM": ("nemotron", "NemotronForCausalLM"),
     "OlmoForCausalLM": ("olmo", "OlmoForCausalLM"),
+    "OlmoeForCausalLM": ("olmoe", "OlmoeForCausalLM"),
     "OPTForCausalLM": ("opt", "OPTForCausalLM"),
     "OrionForCausalLM": ("orion", "OrionForCausalLM"),
     "PersimmonForCausalLM": ("persimmon", "PersimmonForCausalLM"),