iHore/vLLM
8
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[Bugfix] Remove nested torch.compile in GDN rearrange_mixed_qkv causing CUDA graph capture failure (#42070)

Browse Source 
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
Co-authored-by: Jiangyun Zhu <riverclouds.zhu@qq.com>
This commit is contained in:
Thomas Parnell
2026-05-09 08:30:55 -07:00
committed by GitHub
co-authored by Jiangyun Zhu
parent adb6d96516
commit 3dda9aeb54
1 changed files with 0 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
vllm/model_executor/layers/mamba/gdn_linear_attn.py
-1
View File
@@ -637,7 +637,6 @@ class GatedDeltaNetAttention(PluggableLayer, MambaBase):
return mixed_qkv_out, z_out, b_out, a_out
@torch.compile(fullgraph=True)
def rearrange_mixed_qkv(self, mixed_qkv):
"""Split packed qkv into contiguous (1, seq, heads, dim) tensors.