[Bugfix] Use is_integrated to detect UMA GPUs for memory reporting (#35356)

Signed-off-by: haosdent <haosdent@gmail.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
haosdent
2026-04-13 11:07:40 -07:00
committed by GitHub
co-authored by DarkLight1337
parent 739e5945dc
commit 995e9a209e
4 changed files with 83 additions and 16 deletions
+12
View File
@@ -734,6 +734,18 @@ class Platform:
"""
return "vllm.distributed.device_communicators.base_device_communicator.DeviceCommunicatorBase" # noqa
@classmethod
def is_integrated_gpu(cls, device_id: int = 0) -> bool:
"""
Returns whether the GPU is an integrated (UMA) device that shares
system memory with the CPU.
On UMA systems (e.g. NVIDIA GH200, DGX Spark, Jetson Orin),
cudaMemGetInfo may underreport free memory because it does not
account for reclaimable OS memory (page cache, buffers).
"""
return False
@classmethod
def supports_mx(cls) -> bool:
"""