biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Bugfix] Force continuous usage stats when CLI override is enabled (#37923)

Browse Source 
Signed-off-by: Your Name <you@example.com>
Co-authored-by: Your Name <you@example.com>
Co-authored-by: OpenCode <noreply@openai.com>
This commit is contained in:
Dhruv Singal
2026-03-24 10:29:50 -07:00
committed by GitHub
parent a5416bc52e
commit 4df5fa7439
3 changed files with 41 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
tests/entrypoints/openai/chat_completion/test_enable_force_include_usage.py
View File

@@ -54,21 +54,19 @@ async def test_chat_with_enable_force_include_usage(
)
last_completion_tokens = 0
async for chunk in stream:
if not len(chunk.choices):
assert chunk.usage.prompt_tokens >= 0
assert (
last_completion_tokens == 0
or chunk.usage.completion_tokens > last_completion_tokens
or (
not chunk.choices
and chunk.usage.completion_tokens == last_completion_tokens
)
assert chunk.usage.prompt_tokens >= 0
assert (
last_completion_tokens == 0
or chunk.usage.completion_tokens > last_completion_tokens
or (
not chunk.choices
and chunk.usage.completion_tokens == last_completion_tokens
)
assert chunk.usage.total_tokens == (
chunk.usage.prompt_tokens + chunk.usage.completion_tokens
)
else:
assert chunk.usage is None
)
assert chunk.usage.total_tokens == (
chunk.usage.prompt_tokens + chunk.usage.completion_tokens
)
last_completion_tokens = chunk.usage.completion_tokens
@pytest.fixture(scope="module")