zhangyiss/mlx-examples
1
0
Fork 0
mirror of https://github.com/ml-explore/mlx-examples.git synced 2025-10-23 22:18:06 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Add /v1/models endpoint to mlx_lm.server (#984)

Browse Source 
* Add 'models' endpoint to server

* Add test for new 'models' server endpoint

* Check hf_cache for mlx models

* update tests to check hf_cache for models

* simplify test

* doc

---------

Co-authored-by: Awni Hannun <awni@apple.com>
This commit is contained in:
jamesm131
2024-09-29 00:21:11 +10:00
committed by GitHub
parent 76710f61af
commit d812516d3d
3 changed files with 70 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
llms/tests/test_server.py
View File

@@ -1,5 +1,7 @@
# Copyright © 2024 Apple Inc.
import http
import json
import threading
import unittest
@@ -77,6 +79,19 @@ class TestServer(unittest.TestCase):
self.assertIn("id", response_body)
self.assertIn("choices", response_body)
def test_handle_models(self):
url = f"http://localhost:{self.port}/v1/models"
response = requests.get(url)
self.assertEqual(response.status_code, 200)
response_body = json.loads(response.text)
self.assertEqual(response_body["object"], "list")
self.assertIsInstance(response_body["data"], list)
self.assertGreater(len(response_body["data"]), 0)
model = response_body["data"][0]
self.assertIn("id", model)
self.assertEqual(model["object"], "model")
self.assertIn("created", model)
def test_sequence_overlap(self):
from mlx_lm.server import sequence_overlap