File tree Expand file tree Collapse file tree 2 files changed +22
-0
lines changed
docs/contributing/continuous_batching/tests Expand file tree Collapse file tree 2 files changed +22
-0
lines changed Original file line number Diff line number Diff line change 44 Unless otherwise specified, all the continuous batching tests are running with ` max_model_len=256 `
55
66::: tests.e2e.test_spyre_cb
7+ options:
8+ show_root_heading: true
9+
10+ ::: tests.e2e.test_spyre_async_llm
11+ options:
12+ show_root_heading: true
13+ members:
14+ - test_abort
15+
16+ ::: tests.e2e.test_spyre_max_new_tokens
17+ options:
18+ show_root_heading: true
19+ members:
20+ - test_output
21+
22+ ::: tests.e2e.test_spyre_online
23+ options:
24+ show_root_heading: true
25+ members:
26+ - test_openai_serving_cb
Original file line number Diff line number Diff line change @@ -26,6 +26,8 @@ def test_output(
2626 monkeypatch : pytest .MonkeyPatch ,
2727) -> None :
2828 '''
29+ Checks that `max_tokens` parameter of `SamplingParams` works correctly
30+
2931 The warmup is based on a single shape. After the warmup,
3032 one request with the provided prompts is input to vLLM.
3133 The same prompts are also input to HF. The generated output
You can’t perform that action at this time.
0 commit comments