A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 16, 18:15 UTC
[Bugfix][Docs] Update list of mock imports (#7493)
Cyrus Leung committed
Aug 14, 2024 at 11:37 UTC
dd164d72f31f95e19d84756a644811d0ca2c7c59
2 files changed
+3
-1
.buildkite/test-pipeline.yaml
+2
@@ -36,6 +36,8 @@ steps:
36
commands:
37
- pip install -r requirements-docs.txt
38
- SPHINXOPTS=\"-W\" make html
39
+ # Check API reference (if it fails, you may have missing mock imports)
40
+ - grep \"sig sig-object py\" build/html/dev/sampling_params.html
41
42
- label: Async Engine, Inputs, Utils, Worker Test # 15min
43
fast_check: true
docs/source/conf.py
+1
-1
@@ -97,13 +97,13 @@ def setup(app):
97
# Mock out external dependencies here, otherwise the autodoc pages may be blank.
98
autodoc_mock_imports = [
99
"aiohttp",
100
+ "compressed_tensors",
101
"cpuinfo",
102
"torch",
103
"transformers",
104
"psutil",
105
"prometheus_client",
106
"sentencepiece",
106
- "vllm.cuda_utils",
107
"vllm._C",
108
"PIL",
109
"numpy",