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

[Bugfix] Fix DP Attention Padding in Dummy Run (#34187)

Browse Source 
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Benjamin Chislett <bchislett@nvidia.com>
This commit is contained in:
Lucas Wilkinson
2026-02-09 21:29:39 -08:00
committed by GitHub
parent ab97bcf662
commit 81e217fe6b
1 changed files with 1 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
vllm/v1/worker/gpu_model_runner.py
View File

@@ -4787,6 +4787,7 @@ class GPUModelRunner(
pad_attn = cudagraph_runtime_mode == CUDAGraphMode.FULL
attn_metadata, _ = self._build_attention_metadata(
num_tokens=num_tokens_unpadded,
num_tokens_padded=num_tokens_padded if pad_attn else None,
num_reqs=num_reqs_padded,
max_query_len=max_query_len,
ubatch_slices=ubatch_slices_padded if pad_attn else ubatch_slices,