xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-05-25 15:11:20 +08:00
Code Issues Packages Projects Releases Wiki Activity

misc cleanups to prepare for rebase

Browse Source 
Signed-off-by: Sage Moore <sage@neuralmagic.com>
This commit is contained in:
Sage Moore 2025-06-02 18:01:24 +00:00
parent 90e46ee5e3
commit 065816d25f
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/worker/model_runner.py
View File

@ -2122,7 +2122,7 @@ class CUDAGraphRunner(nn.Module):
**kwargs, **kwargs,
) -> torch.Tensor: ) -> torch.Tensor:
attn_metadata: AttentionMetadata = get_forward_context().attn_metadata attn_metadata: AttentionMetadata = get_forward_context().attn_metadata
# Copy the input tensors to the input buffers. # Copy the input tensors to the input buffers.
self.input_buffers["input_ids"].copy_(input_ids, non_blocking=True) self.input_buffers["input_ids"].copy_(input_ids, non_blocking=True)
if positions is not None: if positions is not None: