Skip to content

[CI/Build] Fix AMD CI: test_cpu_gpu.py #27388

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Oct 23, 2025
Merged

[CI/Build] Fix AMD CI: test_cpu_gpu.py #27388

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
d36420d
update tests
zhewenl Oct 23, 2025
834e042
update logic to use current_platform
zhewenl Oct 23, 2025
f8a9123
update
zhewenl Oct 23, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 13 additions & 4 deletions tests/v1/kv_offload/test_cpu_gpu.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,11 +8,20 @@

from vllm.platforms import current_platform
from vllm.v1.attention.backends.flash_attn import FlashAttentionBackend
from vllm.v1.attention.backends.flashinfer import FlashInferBackend
from vllm.v1.attention.backends.mla.flashattn_mla import FlashAttnMLABackend
from vllm.v1.kv_offload.mediums import CPULoadStoreSpec, GPULoadStoreSpec
from vllm.v1.kv_offload.worker.cpu_gpu import CpuGpuOffloadingHandler

BACKENDS_TO_TEST = [FlashAttentionBackend]

if not current_platform.is_rocm():
from vllm.v1.attention.backends.flashinfer import FlashInferBackend

BACKENDS_TO_TEST.append(FlashInferBackend)

from vllm.v1.attention.backends.mla.flashattn_mla import FlashAttnMLABackend

BACKENDS_TO_TEST.append(FlashAttnMLABackend)

NUM_GPU_BLOCKS = [64]
NUM_CPU_BLOCKS = [256]
GPU_BLOCK_SIZES = [16]
Expand Down Expand Up @@ -55,8 +64,8 @@ def test_transfer(
) -> None:
current_platform.seed_everything(seed)

# create per-layer GPU KV caches
attn_backends_list = [FlashAttentionBackend, FlashInferBackend, FlashAttnMLABackend]
# create per-layer GPU KV caches based on available attn_backends
attn_backends_list = BACKENDS_TO_TEST

gpu_caches = {}
attn_backends = {}
Expand Down