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

Add full API docs and improve the UX of navigating them (#17485)

Browse Source 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Harry Mellor
2025-05-04 03:42:43 +01:00
committed by GitHub
parent 46fae69cf0
commit d6484ef3c3
101 changed files with 872 additions and 980 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
vllm/config.py
View File

@@ -1911,10 +1911,10 @@ class SchedulerConfig:
cuda_graph_sizes: list[int] = field(default_factory=lambda: [512])
"""Cuda graph capture sizes, default is 512.
1. if one value is provided, then the capture list would follow the pattern:
[1, 2, 4] + [i for i in range(8, cuda_graph_sizes + 1, 8)]
2. more than one value (e.g. 1 2 128) is provided,
then the capture list will follow the provided list."""
1. if one value is provided, then the capture list would follow the
pattern: [1, 2, 4] + [i for i in range(8, cuda_graph_sizes + 1, 8)]
2. more than one value (e.g. 1 2 128) is provided, then the capture list
will follow the provided list."""
delay_factor: float = 0.0
"""Apply a delay (of delay factor multiplied by previous
@@ -2888,7 +2888,7 @@ class PoolerConfig:
pooling_type: Optional[str] = None
"""
The pooling method of the pooling model. This should be a key in
:class:`vllm.model_executor.layers.pooler.PoolingType`.
{class}`vllm.model_executor.layers.pooler.PoolingType`.
"""
normalize: Optional[bool] = None