[Minor] Add Phi 2 to supported models (#2159)

Author: WoosukKwon

README.md

@@ -65,7 +65,7 @@ vLLM seamlessly supports many Hugging Face models, including the following archi
 - Mixtral (`mistralai/Mixtral-8x7B-v0.1`, `mistralai/Mixtral-8x7B-Instruct-v0.1`, etc.)
 - MPT (`mosaicml/mpt-7b`, `mosaicml/mpt-30b`, etc.)
 - OPT (`facebook/opt-66b`, `facebook/opt-iml-max-30b`, etc.)
-- Phi-1.5 (`microsoft/phi-1_5`, etc.)
+- Phi (`microsoft/phi-1_5`, `microsoft/phi-2`, etc.)
 - Qwen (`Qwen/Qwen-7B`, `Qwen/Qwen-7B-Chat`, etc.)
 - Yi (`01-ai/Yi-6B`, `01-ai/Yi-34B`, etc.)
 

docs/source/models/supported_models.rst

@@ -60,8 +60,8 @@ Alongside each architecture, we include some popular models that use it.
     - OPT, OPT-IML
     - :code:`facebook/opt-66b`, :code:`facebook/opt-iml-max-30b`, etc.
   * - :code:`PhiForCausalLM`
-    - Phi-1.5
-    - :code:`microsoft/phi-1_5`, etc.
+    - Phi
+    - :code:`microsoft/phi-1_5`, :code:`microsoft/phi-2`, etc.
   * - :code:`QWenLMHeadModel`
     - Qwen
     - :code:`Qwen/Qwen-7B`, :code:`Qwen/Qwen-7B-Chat`, etc.

tests/models/test_models.py

@@ -15,12 +15,12 @@
     "EleutherAI/pythia-70m",
     "bigscience/bloom-560m",
     "mosaicml/mpt-7b",
-    "microsoft/phi-1_5",
+    "microsoft/phi-2",
 ]
 
 
 @pytest.mark.parametrize("model", MODELS)
-@pytest.mark.parametrize("dtype", ["half"])
+@pytest.mark.parametrize("dtype", ["float"])
 @pytest.mark.parametrize("max_tokens", [128])
 def test_models(
     hf_runner,