Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in
Toggle navigation
Menu
Open sidebar
OpenDAS
vllm_cscc
Commits
aca5c514
Unverified
Commit
aca5c514
authored
Jan 15, 2026
by
Wentao Ye
Committed by
GitHub
Jan 15, 2026
Browse files
[Refactor] Remove unused file (#32422)
parent
31c29257
Changes
1
Show whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
0 additions
and
28 deletions
+0
-28
vllm/entrypoints/pooling/embed/conftest.py
vllm/entrypoints/pooling/embed/conftest.py
+0
-28
No files found.
vllm/entrypoints/pooling/embed/conftest.py
deleted
100644 → 0
View file @
31c29257
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
"""Pytest configuration for vLLM pooling embed tests."""
import
warnings
import
torch
from
vllm.platforms
import
current_platform
def
pytest_collection_modifyitems
(
config
,
items
):
"""Configure ROCm-specific settings based on collected tests."""
if
not
current_platform
.
is_rocm
():
return
# Disable Flash/MemEfficient SDP on ROCm to avoid HF Transformers
# 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
)
torch
.
backends
.
cuda
.
enable_math_sdp
(
True
)
warnings
.
warn
(
"ROCm: Disabled flash_sdp and mem_efficient_sdp, enabled math_sdp "
"to avoid HuggingFace Transformers accuracy issues"
,
UserWarning
,
stacklevel
=
1
,
)
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment