Map CwmForCausalLM to llama and LlamaForCausalLM (#25611)

Signed-off-by: Jacob Kahn <jacobkahn1@gmail.com>
Co-authored-by: Roger Wang <hey@rogerw.io>

tests/models/registry.py

@@ -196,6 +196,9 @@ _TEXT_GENERATION_EXAMPLE_MODELS = {
                                          trust_remote_code=True),
     "Cohere2ForCausalLM": _HfExamplesInfo("CohereForAI/c4ai-command-r7b-12-2024", # noqa: E501
                                          trust_remote_code=True),
+    "CwmForCausalLM": _HfExamplesInfo("facebook/cwm", # noqa: E501
+                                      trust_remote_code=True,
+                                      is_available_online=False),
     "DbrxForCausalLM": _HfExamplesInfo("databricks/dbrx-instruct"),
     "DeciLMForCausalLM": _HfExamplesInfo("nvidia/Llama-3_3-Nemotron-Super-49B-v1", # noqa: E501
                                          trust_remote_code=True),

vllm/model_executor/models/registry.py

@@ -64,6 +64,7 @@ _TEXT_GENERATION_MODELS = {
     "ChatGLMForConditionalGeneration": ("chatglm", "ChatGLMForCausalLM"),
     "CohereForCausalLM": ("commandr", "CohereForCausalLM"),
     "Cohere2ForCausalLM": ("commandr", "CohereForCausalLM"),
+    "CwmForCausalLM": ("llama", "LlamaForCausalLM"),
     "DbrxForCausalLM": ("dbrx", "DbrxForCausalLM"),
     "DeciLMForCausalLM": ("nemotron_nas", "DeciLMForCausalLM"),
     "DeepseekForCausalLM": ("deepseek", "DeepseekForCausalLM"),