Skip to content

Update instance gpu info #5119

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.

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 1 commit into from
Apr 5, 2025
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
60 changes: 30 additions & 30 deletions src/sagemaker/image_uri_config/instance_gpu_info.json
Original file line number Diff line number Diff line change
Expand Up @@ -23,7 +23,7 @@
"ml.g5.16xlarge": {"Count": 1, "TotalGpuMemoryInMiB": 24576},
"ml.g5.12xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.24xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 196608}
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 183104}
},
"ap-east-1": {
"ml.p5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 655360},
Expand All @@ -49,7 +49,7 @@
"ml.g5.16xlarge": {"Count": 1, "TotalGpuMemoryInMiB": 24576},
"ml.g5.12xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.24xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 196608}
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 183104}
},
"ap-northeast-1": {
"ml.p5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 655360},
Expand All @@ -75,7 +75,7 @@
"ml.g5.16xlarge": {"Count": 1, "TotalGpuMemoryInMiB": 24576},
"ml.g5.12xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.24xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 196608}
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 183104}
},
"ap-northeast-2": {
"ml.p5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 655360},
Expand All @@ -101,7 +101,7 @@
"ml.g5.16xlarge": {"Count": 1, "TotalGpuMemoryInMiB": 24576},
"ml.g5.12xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.24xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 196608}
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 183104}
},
"ap-northeast-3": {
"ml.p5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 655360},
Expand All @@ -127,7 +127,7 @@
"ml.g5.16xlarge": {"Count": 1, "TotalGpuMemoryInMiB": 24576},
"ml.g5.12xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.24xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 196608}
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 183104}
},
"ap-south-1": {
"ml.p5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 655360},
Expand All @@ -153,7 +153,7 @@
"ml.g5.16xlarge": {"Count": 1, "TotalGpuMemoryInMiB": 24576},
"ml.g5.12xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.24xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 196608}
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 183104}
},
"ap-southeast-1": {
"ml.p5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 655360},
Expand All @@ -179,7 +179,7 @@
"ml.g5.16xlarge": {"Count": 1, "TotalGpuMemoryInMiB": 24576},
"ml.g5.12xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.24xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 196608}
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 183104}
},
"ap-southeast-2": {
"ml.p5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 655360},
Expand All @@ -205,7 +205,7 @@
"ml.g5.16xlarge": {"Count": 1, "TotalGpuMemoryInMiB": 24576},
"ml.g5.12xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.24xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 196608}
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 183104}
},
"ap-southeast-3": {
"ml.p5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 655360},
Expand All @@ -231,7 +231,7 @@
"ml.g5.16xlarge": {"Count": 1, "TotalGpuMemoryInMiB": 24576},
"ml.g5.12xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.24xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 196608}
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 183104}
},
"ca-central-1": {
"ml.p5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 655360},
Expand All @@ -257,7 +257,7 @@
"ml.g5.16xlarge": {"Count": 1, "TotalGpuMemoryInMiB": 24576},
"ml.g5.12xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.24xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 196608}
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 183104}
},
"cn-north-1": {
"ml.p5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 655360},
Expand All @@ -283,7 +283,7 @@
"ml.g5.16xlarge": {"Count": 1, "TotalGpuMemoryInMiB": 24576},
"ml.g5.12xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.24xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 196608}
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 183104}
},
"cn-northwest-1": {
"ml.p5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 655360},
Expand All @@ -309,7 +309,7 @@
"ml.g5.16xlarge": {"Count": 1, "TotalGpuMemoryInMiB": 24576},
"ml.g5.12xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.24xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 196608}
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 183104}
},
"eu-central-1": {
"ml.p5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 655360},
Expand All @@ -335,7 +335,7 @@
"ml.g5.16xlarge": {"Count": 1, "TotalGpuMemoryInMiB": 24576},
"ml.g5.12xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.24xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 196608}
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 183104}
},
"eu-central-2": {
"ml.p5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 655360},
Expand All @@ -361,7 +361,7 @@
"ml.g5.16xlarge": {"Count": 1, "TotalGpuMemoryInMiB": 24576},
"ml.g5.12xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.24xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 196608}
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 183104}
},
"eu-north-1": {
"ml.p5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 655360},
Expand All @@ -387,7 +387,7 @@
"ml.g5.16xlarge": {"Count": 1, "TotalGpuMemoryInMiB": 24576},
"ml.g5.12xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.24xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 196608}
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 183104}
},
"eu-south-1": {
"ml.p5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 655360},
Expand All @@ -413,7 +413,7 @@
"ml.g5.16xlarge": {"Count": 1, "TotalGpuMemoryInMiB": 24576},
"ml.g5.12xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.24xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 196608}
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 183104}
},
"eu-south-2": {
"ml.p5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 655360},
Expand All @@ -439,7 +439,7 @@
"ml.g5.16xlarge": {"Count": 1, "TotalGpuMemoryInMiB": 24576},
"ml.g5.12xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.24xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 196608}
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 183104}
},
"eu-west-1": {
"ml.p5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 655360},
Expand All @@ -465,7 +465,7 @@
"ml.g5.16xlarge": {"Count": 1, "TotalGpuMemoryInMiB": 24576},
"ml.g5.12xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.24xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 196608}
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 183104}
},
"eu-west-2": {
"ml.p5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 655360},
Expand All @@ -491,7 +491,7 @@
"ml.g5.16xlarge": {"Count": 1, "TotalGpuMemoryInMiB": 24576},
"ml.g5.12xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.24xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 196608}
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 183104}
},
"eu-west-3": {
"ml.p5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 655360},
Expand All @@ -517,7 +517,7 @@
"ml.g5.16xlarge": {"Count": 1, "TotalGpuMemoryInMiB": 24576},
"ml.g5.12xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.24xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 196608}
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 183104}
},
"il-central-1": {
"ml.p5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 655360},
Expand All @@ -543,7 +543,7 @@
"ml.g5.16xlarge": {"Count": 1, "TotalGpuMemoryInMiB": 24576},
"ml.g5.12xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.24xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 196608}
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 183104}
},
"me-central-1": {
"ml.p5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 655360},
Expand All @@ -569,7 +569,7 @@
"ml.g5.16xlarge": {"Count": 1, "TotalGpuMemoryInMiB": 24576},
"ml.g5.12xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.24xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 196608}
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 183104}
},
"me-south-1": {
"ml.p5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 655360},
Expand All @@ -595,7 +595,7 @@
"ml.g5.16xlarge": {"Count": 1, "TotalGpuMemoryInMiB": 24576},
"ml.g5.12xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.24xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 196608}
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 183104}
},
"sa-east-1": {
"ml.p5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 655360},
Expand All @@ -621,7 +621,7 @@
"ml.g5.16xlarge": {"Count": 1, "TotalGpuMemoryInMiB": 24576},
"ml.g5.12xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.24xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 196608}
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 183104}
},
"us-east-1": {
"ml.p5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 655360},
Expand All @@ -647,7 +647,7 @@
"ml.g5.16xlarge": {"Count": 1, "TotalGpuMemoryInMiB": 24576},
"ml.g5.12xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.24xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 196608}
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 183104}
},
"us-east-2": {
"ml.p5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 655360},
Expand All @@ -673,7 +673,7 @@
"ml.g5.16xlarge": {"Count": 1, "TotalGpuMemoryInMiB": 24576},
"ml.g5.12xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.24xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 196608}
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 183104}
},
"us-gov-east-1": {
"ml.p5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 655360},
Expand All @@ -699,7 +699,7 @@
"ml.g5.16xlarge": {"Count": 1, "TotalGpuMemoryInMiB": 24576},
"ml.g5.12xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.24xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 196608}
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 183104}
},
"us-gov-west-1": {
"ml.p5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 655360},
Expand All @@ -725,7 +725,7 @@
"ml.g5.16xlarge": {"Count": 1, "TotalGpuMemoryInMiB": 24576},
"ml.g5.12xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.24xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 196608}
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 183104}
},
"us-west-1": {
"ml.p5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 655360},
Expand All @@ -751,7 +751,7 @@
"ml.g5.16xlarge": {"Count": 1, "TotalGpuMemoryInMiB": 24576},
"ml.g5.12xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.24xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 196608}
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 183104}
},
"us-west-2": {
"ml.p5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 655360},
Expand All @@ -777,6 +777,6 @@
"ml.g5.16xlarge": {"Count": 1, "TotalGpuMemoryInMiB": 24576},
"ml.g5.12xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.24xlarge": {"Count": 4, "TotalGpuMemoryInMiB": 98304},
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 196608}
"ml.g5.48xlarge": {"Count": 8, "TotalGpuMemoryInMiB": 183104}
}
}
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,7 @@
REGION = "us-west-2"
VALID_INSTANCE_TYPE = "ml.g5.48xlarge"
INVALID_INSTANCE_TYPE = "fl.c5.57xxlarge"
EXPECTED_INSTANCE_GPU_INFO = (8, 196608)
EXPECTED_INSTANCE_GPU_INFO = (8, 183104)


def test_get_gpu_info_success(sagemaker_session):
Expand Down
4 changes: 2 additions & 2 deletions tests/unit/sagemaker/serve/utils/test_hardware_detector.py
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,7 @@
REGION = "us-west-2"
VALID_INSTANCE_TYPE = "ml.g5.48xlarge"
INVALID_INSTANCE_TYPE = "fl.c5.57xxlarge"
EXPECTED_INSTANCE_GPU_INFO = (8, 196608)
EXPECTED_INSTANCE_GPU_INFO = (8, 183104)
MIB_CONVERSION_FACTOR = 0.00000095367431640625
MEMORY_BUFFER_MULTIPLIER = 1.2 # 20% buffer

Expand All @@ -39,7 +39,7 @@ def test_get_gpu_info_success(sagemaker_session, boto_session):
"MemoryInfo": {"SizeInMiB": 24576},
}
],
"TotalGpuMemoryInMiB": 196608,
"TotalGpuMemoryInMiB": 183104,
},
}
]
Expand Down