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

replace cuda_device_count_stateless() to current_platform.device_count() (#37841)

Browse Source 
Signed-off-by: Liao, Wei <wei.liao@intel.com>
Signed-off-by: wliao2 <wei.liao@intel.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
This commit is contained in:
wliao2
2026-03-31 07:32:54 -07:00
committed by GitHub
parent e8057c00bc
commit 4dfad17ed1
20 changed files with 96 additions and 92 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tools/pre_commit/check_torch_cuda.py
View File

@@ -10,6 +10,8 @@ import regex as re
_TORCH_CUDA_PATTERNS = [
r"\btorch\.cuda\.(empty_cache|synchronize|device_count|current_device|memory_reserved|memory_allocated|max_memory_allocated|max_memory_reserved|reset_peak_memory_stats|memory_stats|set_device|device\()\b",
r"\bwith\storch\.cuda\.device\b",
# Calls torch.cuda.{_is_compiled/_device_count_amdsmi/_device_count_nvml} internally
r"\bcuda_device_count_stateless\(\)\b",
]
ALLOWED_FILES = {"vllm/platforms/", "vllm/device_allocator/"}