apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-12-24 13:28:13 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

add detoken switch (#5463)
Some checks failed
CE Compile Job / ce_job_pre_check (push) Has been cancelled
Details
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
Details
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
Details
CE Compile Job / Show Code Archive Output (push) Has been cancelled
Details
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
Details
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
Details
CE Compile Job / CE_UPLOAD (push) Has been cancelled
Details
Deploy GitHub Pages / deploy (push) Has been cancelled
Details

Browse Source
This commit is contained in:
qwes5s5
2025-12-10 21:44:02 +08:00
committed by GitHub
parent 3bdd54ef6e
commit d79438bb86
7 changed files with 77 additions and 32 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
tests/entrypoints/openai/test_serving_chat.py
View File

@@ -60,7 +60,7 @@ class TestOpenAIServingCompletion(unittest.IsolatedAsyncioTestCase):
) as mock_decode:
mock_decode.side_effect = ["token1", "token2", "token3", "token4", "token5", "token6"]
result = self.chat_completion_handler._build_prompt_logprobs(prompt_logprobs_tensors, num_logprobs)
result = self.chat_completion_handler._build_prompt_logprobs(prompt_logprobs_tensors, num_logprobs, True)
# Verify result structure (first element is None, then actual results)
self.assertEqual(len(result), num_prompt_tokens + 1)
@@ -98,7 +98,7 @@ class TestOpenAIServingCompletion(unittest.IsolatedAsyncioTestCase):
) as mock_decode:
mock_decode.side_effect = ["hello", "world"]
result = self.chat_completion_handler._build_prompt_logprobs(prompt_logprobs_tensors, -1)
result = self.chat_completion_handler._build_prompt_logprobs(prompt_logprobs_tensors, -1, True)
self.assertEqual(len(result), num_prompt_tokens + 1)
self.assertIsNone(result[0])
@@ -125,7 +125,7 @@ class TestOpenAIServingCompletion(unittest.IsolatedAsyncioTestCase):
) as mock_decode:
mock_decode.return_value = "single_token"
result = self.chat_completion_handler._build_prompt_logprobs(prompt_logprobs_tensors, num_logprobs)
result = self.chat_completion_handler._build_prompt_logprobs(prompt_logprobs_tensors, num_logprobs, True)
self.assertEqual(len(result), num_prompt_tokens + 1)
self.assertIsNone(result[0])
@@ -154,7 +154,7 @@ class TestOpenAIServingCompletion(unittest.IsolatedAsyncioTestCase):
) as mock_decode:
mock_decode.side_effect = ["t1", "t2", "t3", "t4", "t5", "t6"]
result = self.chat_completion_handler._build_prompt_logprobs(prompt_logprobs_tensors, num_logprobs)
result = self.chat_completion_handler._build_prompt_logprobs(prompt_logprobs_tensors, num_logprobs, True)
self.assertEqual(len(result), num_prompt_tokens + 1)
self.assertIsNone(result[0])
@@ -188,7 +188,7 @@ class TestOpenAIServingCompletion(unittest.IsolatedAsyncioTestCase):
prompt_logprobs_tensors = LogprobsTensors(token_ids, logprobs, ranks)
result = self.chat_completion_handler._build_prompt_logprobs(prompt_logprobs_tensors, num_logprobs)
result = self.chat_completion_handler._build_prompt_logprobs(prompt_logprobs_tensors, num_logprobs, True)
self.assertEqual(len(result), num_prompt_tokens + 1)
self.assertIsNone(result[0])

10
tests/entrypoints/openai/test_serving_completion.py
View File

@@ -208,7 +208,7 @@ class TestOpenAIServingCompletion(unittest.IsolatedAsyncioTestCase):
) as mock_decode:
mock_decode.side_effect = ["token1", "token2", "token3", "token4", "token5", "token6"]
result = self.serving_completion._build_prompt_logprobs(prompt_logprobs_tensors, num_logprobs)
result = self.serving_completion._build_prompt_logprobs(prompt_logprobs_tensors, num_logprobs, True)
# Verify result structure (first element is None, then actual results)
self.assertEqual(len(result), num_prompt_tokens + 1)
@@ -246,7 +246,7 @@ class TestOpenAIServingCompletion(unittest.IsolatedAsyncioTestCase):
) as mock_decode:
mock_decode.side_effect = ["hello", "world"]
result = self.serving_completion._build_prompt_logprobs(prompt_logprobs_tensors, -1)
result = self.serving_completion._build_prompt_logprobs(prompt_logprobs_tensors, -1, True)
self.assertEqual(len(result), num_prompt_tokens + 1)
self.assertIsNone(result[0])
@@ -273,7 +273,7 @@ class TestOpenAIServingCompletion(unittest.IsolatedAsyncioTestCase):
) as mock_decode:
mock_decode.return_value = "single_token"
result = self.serving_completion._build_prompt_logprobs(prompt_logprobs_tensors, num_logprobs)
result = self.serving_completion._build_prompt_logprobs(prompt_logprobs_tensors, num_logprobs, True)
self.assertEqual(len(result), num_prompt_tokens + 1)
self.assertIsNone(result[0])
@@ -302,7 +302,7 @@ class TestOpenAIServingCompletion(unittest.IsolatedAsyncioTestCase):
) as mock_decode:
mock_decode.side_effect = ["t1", "t2", "t3", "t4", "t5", "t6"]
result = self.serving_completion._build_prompt_logprobs(prompt_logprobs_tensors, num_logprobs)
result = self.serving_completion._build_prompt_logprobs(prompt_logprobs_tensors, num_logprobs, True)
self.assertEqual(len(result), num_prompt_tokens + 1)
self.assertIsNone(result[0])
@@ -336,7 +336,7 @@ class TestOpenAIServingCompletion(unittest.IsolatedAsyncioTestCase):
prompt_logprobs_tensors = LogprobsTensors(token_ids, logprobs, ranks)
result = self.serving_completion._build_prompt_logprobs(prompt_logprobs_tensors, num_logprobs)
result = self.serving_completion._build_prompt_logprobs(prompt_logprobs_tensors, num_logprobs, True)
self.assertEqual(len(result), num_prompt_tokens + 1)
self.assertIsNone(result[0])