xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-13 18:25:40 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix entrypoint tests for embedding models (#14052)

Browse Source
This commit is contained in:
Harry Mellor 2025-02-28 16:56:44 +00:00 committed by GitHub
parent 2aed2c9fa7
commit 4be4b26cb7
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 11 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
tests/entrypoints/openai/test_embedding.py
View File

@ -27,7 +27,7 @@ def server():
"bfloat16", "bfloat16",
"--enforce-eager", "--enforce-eager",
"--max-model-len", "--max-model-len",
"8192", "512",
"--chat-template", "--chat-template",
DUMMY_CHAT_TEMPLATE, DUMMY_CHAT_TEMPLATE,
] ]
@ -60,10 +60,10 @@ async def test_single_embedding(client: openai.AsyncOpenAI, model_name: str):
assert embeddings.id is not None assert embeddings.id is not None
assert len(embeddings.data) == 1 assert len(embeddings.data) == 1
assert len(embeddings.data[0].embedding) == 4096 assert len(embeddings.data[0].embedding) == 384
assert embeddings.usage.completion_tokens == 0 assert embeddings.usage.completion_tokens == 0
assert embeddings.usage.prompt_tokens == 9 assert embeddings.usage.prompt_tokens == 11
assert embeddings.usage.total_tokens == 9 assert embeddings.usage.total_tokens == 11
# test using token IDs # test using token IDs
input_tokens = [1, 1, 1, 1, 1] input_tokens = [1, 1, 1, 1, 1]
@ -77,7 +77,7 @@ async def test_single_embedding(client: openai.AsyncOpenAI, model_name: str):
assert embeddings.id is not None assert embeddings.id is not None
assert len(embeddings.data) == 1 assert len(embeddings.data) == 1
assert len(embeddings.data[0].embedding) == 4096 assert len(embeddings.data[0].embedding) == 384
assert embeddings.usage.completion_tokens == 0 assert embeddings.usage.completion_tokens == 0
assert embeddings.usage.prompt_tokens == 5 assert embeddings.usage.prompt_tokens == 5
assert embeddings.usage.total_tokens == 5 assert embeddings.usage.total_tokens == 5
@ -101,10 +101,10 @@ async def test_batch_embedding(client: openai.AsyncOpenAI, model_name: str):
assert embeddings.id is not None assert embeddings.id is not None
assert len(embeddings.data) == 3 assert len(embeddings.data) == 3
assert len(embeddings.data[0].embedding) == 4096 assert len(embeddings.data[0].embedding) == 384
assert embeddings.usage.completion_tokens == 0 assert embeddings.usage.completion_tokens == 0
assert embeddings.usage.prompt_tokens == 32 assert embeddings.usage.prompt_tokens == 33
assert embeddings.usage.total_tokens == 32 assert embeddings.usage.total_tokens == 33
# test List[List[int]] # test List[List[int]]
input_tokens = [[4, 5, 7, 9, 20], [15, 29, 499], [24, 24, 24, 24, 24], input_tokens = [[4, 5, 7, 9, 20], [15, 29, 499], [24, 24, 24, 24, 24],
@ -119,7 +119,7 @@ async def test_batch_embedding(client: openai.AsyncOpenAI, model_name: str):
assert embeddings.id is not None assert embeddings.id is not None
assert len(embeddings.data) == 4 assert len(embeddings.data) == 4
assert len(embeddings.data[0].embedding) == 4096 assert len(embeddings.data[0].embedding) == 384
assert embeddings.usage.completion_tokens == 0 assert embeddings.usage.completion_tokens == 0
assert embeddings.usage.prompt_tokens == 17 assert embeddings.usage.prompt_tokens == 17
assert embeddings.usage.total_tokens == 17 assert embeddings.usage.total_tokens == 17
@ -234,7 +234,7 @@ async def test_single_embedding_truncation(client: openai.AsyncOpenAI,
assert embeddings.id is not None assert embeddings.id is not None
assert len(embeddings.data) == 1 assert len(embeddings.data) == 1
assert len(embeddings.data[0].embedding) == 4096 assert len(embeddings.data[0].embedding) == 384
assert embeddings.usage.completion_tokens == 0 assert embeddings.usage.completion_tokens == 0
assert embeddings.usage.prompt_tokens == 10 assert embeddings.usage.prompt_tokens == 10
assert embeddings.usage.total_tokens == 10 assert embeddings.usage.total_tokens == 10
@ -252,7 +252,7 @@ async def test_single_embedding_truncation(client: openai.AsyncOpenAI,
assert embeddings.id is not None assert embeddings.id is not None
assert len(embeddings.data) == 1 assert len(embeddings.data) == 1
assert len(embeddings.data[0].embedding) == 4096 assert len(embeddings.data[0].embedding) == 384
assert embeddings.usage.completion_tokens == 0 assert embeddings.usage.completion_tokens == 0
assert embeddings.usage.prompt_tokens == 10 assert embeddings.usage.prompt_tokens == 10
assert embeddings.usage.total_tokens == 10 assert embeddings.usage.total_tokens == 10