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

[Docs] Fix warnings in mkdocs build (continued) (#24092)

Browse Source 
Signed-off-by: Zerohertz <ohg3417@gmail.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
This commit is contained in:
Hyogeun Oh (오효근)
2025-09-10 22:23:28 +09:00
committed by GitHub
parent c0bd6a684a
commit ccee371e86
10 changed files with 337 additions and 342 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
vllm/model_executor/layers/quantization/kernels/mixed_precision/__init__.py
View File

@@ -46,11 +46,11 @@ def choose_mp_linear_kernel(
performance.
Args:
config (MPLinearLayerConfig): Description of the linear layer to be
implemented.
config (MPLinearLayerConfig): Description of the linear layer to be
implemented.
compute_capability (Optional[int], optional): The compute capability of
the target device, if None uses `current_platform` to get the compute
capability. Defaults to None.
the target device, if None uses `current_platform` to get
the compute capability. Defaults to None.
Raises:
ValueError: If no kernel can implement the given config.