xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-09 23:54:56 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Docs] Fix griffe warnings in vllm/lora/ops (#25369)

Browse Source 
Signed-off-by: windsonsea <haifeng.yao@daocloud.io>
This commit is contained in:
Michael Yao 2025-09-23 11:42:58 +08:00 committed by GitHub
parent 78237e43bf
commit fafbe11af4
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 3 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
vllm/lora/ops/triton_ops/lora_kernel_metadata.py
View File

@ -83,8 +83,8 @@ class LoRAKernelMeta:
Prepare kernel metadata tensors for the current forward pass.
Args:
token_lora_tensor (torch.Tensor): Tensor containing lora indices
for each input token.
token_lora_mapping (torch.Tensor): Tensor containing lora indices
for each input token.
"""
self._reset()
@ -136,7 +136,7 @@ class LoRAKernelMeta:
Args:
token_nums (int): Number of input tokens in the current forward
pass.
pass of the kernel.
"""
return (
self.token_lora_mapping[:token_nums],

1
vllm/lora/ops/xla_ops/lora_ops.py
View File

@ -93,7 +93,6 @@ def bgmv_shrink(
inputs (torch.Tensor): Input tensor of shape [num_tokens, hidden_size].
lora_b_weights (torch.Tensor): LoRA weights of shape
[num_loras, lora_rank, hidden_size].
output_tensor (torch.Tensor): (Unused) output tensor (placeholder).
lora_indices_tensor (torch.Tensor): Tensor of shape [num_tokens]
indicating which LoRA matrix to use for each token.
scaling (float, optional): Scalar multiplier applied to the output.