[Dependency] Upgrade FlashInfer version to 0.7.0 (#58069)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com> Co-authored-by: Codex <noreply@openai.com> Co-authored-by: Yongye Zhu <zyy1102000@gmail.com> Co-authored-by: Kevin H. Luu <khluu000@gmail.com>
This commit is contained in:
co-authored by
Codex
Yongye Zhu
Kevin H. Luu
parent
a1b6763df6
commit
44bf011f44
@@ -0,0 +1,21 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||
|
||||
import pytest
|
||||
import torch
|
||||
|
||||
from vllm import envs
|
||||
from vllm.platforms import current_platform
|
||||
|
||||
|
||||
@pytest.fixture(autouse=True)
|
||||
def skip_unsupported_flashinfer_sampler():
|
||||
# CI runs this suite with FlashInfer both explicitly enabled and disabled.
|
||||
if (
|
||||
current_platform.is_cuda()
|
||||
and envs.is_set("VLLM_USE_FLASHINFER_SAMPLER")
|
||||
and envs.VLLM_USE_FLASHINFER_SAMPLER
|
||||
and current_platform.num_compute_units(torch.accelerator.current_device_index())
|
||||
<= 16
|
||||
):
|
||||
pytest.skip("FlashInfer top-k masking requires more than 16 SMs")
|
||||
Reference in New Issue
Block a user