A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 17, 04:15 UTC
fix lint
simon-mo committed
Mar 15, 2024 at 22:23 UTC
ad50bf4b25ba4344a560a7919fdc6ddb57c3d808
2 files changed
+3
-3
.github/workflows/ruff.yml
+1
-1
@@ -31,4 +31,4 @@ jobs:
31
ruff vllm tests
32
- name: Spelling check with codespell
33
run: |
34
- codespell --toml pyproject.toml
\ No newline at end of file
34
+ codespell --toml pyproject.toml
\ No newline at end of file
tests/kernels/test_prefix_prefill.py
+2
-2
@@ -36,8 +36,8 @@ def test_contexted_kv_attention(
36
torch.cuda.manual_seed(0)
37
torch.set_default_device(device)
38
39
- # Need this, otherwise when we capture the graph the process for GPU 1 would run on both
40
- # GPU0 and GPU1 and things would hang
39
+ # Need this, otherwise when we capture the graph the process for GPU 1 would
40
+ # run on both GPU0 and GPU1 and things would hang
41
#
42
# see also similar issue: https://github.com/Dao-AILab/flash-attention/issues/523
43
torch.cuda.set_device(device)