lidanger
diff --git a/‎llama_cpp/server/app.py
Copy file name to clipboardExpand all lines: llama_cpp/server/app.py
+2Lines changed: 2 additions & 0 deletions b/‎llama_cpp/server/app.py
Copy file name to clipboardExpand all lines: llama_cpp/server/app.py
+2Lines changed: 2 additions & 0 deletions
diff --git a/‎poetry.lock
Copy file name to clipboardExpand all lines: poetry.lock
+93-2Lines changed: 93 additions & 2 deletions b/‎poetry.lock
Copy file name to clipboardExpand all lines: poetry.lock
+93-2Lines changed: 93 additions & 2 deletions
diff --git a/‎pyproject.toml
Copy file name to clipboardExpand all lines: pyproject.toml
+1Lines changed: 1 addition & 0 deletions b/‎pyproject.toml
Copy file name to clipboardExpand all lines: pyproject.toml
+1Lines changed: 1 addition & 0 deletions
diff --git a/‎tests/test_llama.py
Copy file name to clipboardExpand all lines: tests/test_llama.py
+21Lines changed: 21 additions & 0 deletions b/‎tests/test_llama.py
Copy file name to clipboardExpand all lines: tests/test_llama.py
+21Lines changed: 21 additions & 0 deletions
@@ -24,6 +24,7 @@ class Settings(BaseSettings):
     last_n_tokens_size: int = 64
     logits_all: bool = False
     cache: bool = False  # WARNING: This is an experimental feature
+    vocab_only: bool = False
 
 
 app = FastAPI(
@@ -49,6 +50,7 @@ class Settings(BaseSettings):
     n_batch=settings.n_batch,
     n_ctx=settings.n_ctx,
     last_n_tokens_size=settings.last_n_tokens_size,
+    vocab_only=settings.vocab_only,
 )
 if settings.cache:
     cache = llama_cpp.LlamaCache()
 
@@ -24,6 +24,7 @@ mkdocs = "^1.4.2"
 mkdocstrings = {extras = ["python"], version = "^0.20.0"}
 mkdocs-material = "^9.1.4"
 pytest = "^7.2.2"
+httpx = "^0.24.0"
 
 [build-system]
 requires = [
 
@@ -128,3 +128,24 @@ def mock_sample(*args, **kwargs):
     n = 0  # reset
     completion = llama.create_completion("", max_tokens=1)
     assert completion["choices"][0]["text"] == ""
+
+
+def test_llama_server():
+    from fastapi.testclient import TestClient
+    import os
+    os.environ["MODEL"] = MODEL
+    os.environ["VOCAB_ONLY"] = "true"
+    from llama_cpp.server.app import app
+    client = TestClient(app)
+    response = client.get("/v1/models")
+    assert response.json() == {
+        "object": "list",
+        "data": [
+            {
+                "id": MODEL,
+                "object": "model",
+                "owned_by": "me",
+                "permissions": [],
+            }
+        ],
+    }