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

[ROCm][Bugfix] Fix RuntimeError in MMEncoderAttention by replacing .view() with .reshape() (#31203)

Browse Source 
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
This commit is contained in:
Andreas Karatzas
2025-12-23 15:48:01 -06:00
committed by GitHub
parent f790068600
commit bfa2c0bbb9
2 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/models/multimodal/conftest.py
View File

@@ -19,7 +19,7 @@ def pytest_collection_modifyitems(config, items):
return
# Disable Flash/MemEfficient SDP on ROCm to avoid HF Transformers
# accuracy issues
# accuracy issues: https://github.com/vllm-project/vllm/issues/30167
# TODO: Remove once ROCm SDP accuracy issues are resolved on HuggingFace
torch.backends.cuda.enable_flash_sdp(False)
torch.backends.cuda.enable_mem_efficient_sdp(False)