EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

Refine OpenAI serving entrypoint to remove batch requests (#7372)

Browse Source 
Signed-off-by: Xinyuan Tong <justinning0323@outlook.com>
Co-authored-by: Chang Su <csu272@usc.edu>
This commit is contained in:
Xinyuan Tong
2025-06-20 14:33:43 -07:00
committed by GitHub
parent 794be55af2
commit 0998808009
8 changed files with 488 additions and 645 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
test/srt/openai/test_serving_completions.py
View File

@@ -36,12 +36,12 @@ class ServingCompletionTestCase(unittest.TestCase):
# ---------- prompt-handling ----------
def test_single_string_prompt(self):
req = CompletionRequest(model="x", prompt="Hello world", max_tokens=100)
internal, _ = self.sc._convert_to_internal_request([req], ["id"])
internal, _ = self.sc._convert_to_internal_request(req)
self.assertEqual(internal.text, "Hello world")
def test_single_token_ids_prompt(self):
req = CompletionRequest(model="x", prompt=[1, 2, 3, 4], max_tokens=100)
internal, _ = self.sc._convert_to_internal_request([req], ["id"])
internal, _ = self.sc._convert_to_internal_request(req)
self.assertEqual(internal.input_ids, [1, 2, 3, 4])
def test_completion_template_handling(self):
@@ -55,7 +55,7 @@ class ServingCompletionTestCase(unittest.TestCase):
"sglang.srt.entrypoints.openai.serving_completions.generate_completion_prompt_from_request",
return_value="processed_prompt",
):
internal, _ = self.sc._convert_to_internal_request([req], ["id"])
internal, _ = self.sc._convert_to_internal_request(req)
self.assertEqual(internal.text, "processed_prompt")
# ---------- echo-handling ----------