Skip to content

change: routing logic change for Hugging Face DLCs #5960

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.

Sign up for GitHub

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

Open
dwarez wants to merge 4 commits into
base: master
Choose a base branch
from
Open

change: routing logic change for Hugging Face DLCs #5960

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
ec1e2b2
fix: updated metadata for huggingface-pytorch-training and
dwarez Jun 17, 2026
9883435
feat(serve): route HuggingFace models to vLLM/SGLang/vLLM-omni in Mod…
dwarez Jun 18, 2026
103ebce
fix: dropping redundant task `visual-question-answering`, it's overruled
dwarez Jun 18, 2026
494d2c2
add: text-ranking to TEI tasks
dwarez Jun 18, 2026
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
66 changes: 66 additions & 0 deletions sagemaker-core/src/sagemaker/core/image_uri_config/huggingface-sglang.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,66 @@
{
"inference": {
"processors": [
"gpu"
],
"version_aliases": {
"0.5": "0.5.8"
},
"versions": {
"0.5.8": {
"py_versions": [
"py312"
],
"registries": {
"af-south-1": "626614931356",
"ap-east-1": "871362719292",
"ap-east-2": "975050140332",
"ap-northeast-1": "763104351884",
"ap-northeast-2": "763104351884",
"ap-northeast-3": "364406365360",
"ap-south-1": "763104351884",
"ap-south-2": "772153158452",
"ap-southeast-1": "763104351884",
"ap-southeast-2": "763104351884",
"ap-southeast-3": "907027046896",
"ap-southeast-4": "457447274322",
"ap-southeast-5": "550225433462",
"ap-southeast-6": "633930458069",
"ap-southeast-7": "590183813437",
"ca-central-1": "763104351884",
"ca-west-1": "204538143572",
"cn-north-1": "727897471807",
"cn-northwest-1": "727897471807",
"eu-central-1": "763104351884",
"eu-central-2": "380420809688",
"eu-north-1": "763104351884",
"eu-south-1": "692866216735",
"eu-south-2": "503227376785",
"eu-west-1": "763104351884",
"eu-west-2": "763104351884",
"eu-west-3": "763104351884",
"il-central-1": "780543022126",
"me-central-1": "914824155844",
"me-south-1": "217643126080",
"mx-central-1": "637423239942",
"sa-east-1": "763104351884",
"us-east-1": "763104351884",
"us-east-2": "763104351884",
"us-gov-east-1": "446045086412",
"us-gov-west-1": "442386744353",
"us-iso-east-1": "886529160074",
"us-isob-east-1": "094389454867",
"us-isof-east-1": "303241398832",
"us-isof-south-1": "454834333376",
"us-west-1": "763104351884",
"us-west-2": "763104351884"
},
"tag_prefix": "0.5.8-transformers4.57.3",
"repository": "huggingface-sglang",
"container_version": {
"gpu": "cu129-ubuntu24.04"
}
}
}
}
}
66 changes: 66 additions & 0 deletions sagemaker-core/src/sagemaker/core/image_uri_config/huggingface-vllm-omni.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,66 @@
{
"inference": {
"processors": [
"gpu"
],
"version_aliases": {
"0.20": "0.20.0"
},
"versions": {
"0.20.0": {
"py_versions": [
"py312"
],
"registries": {
"af-south-1": "626614931356",
"ap-east-1": "871362719292",
"ap-east-2": "975050140332",
"ap-northeast-1": "763104351884",
"ap-northeast-2": "763104351884",
"ap-northeast-3": "364406365360",
"ap-south-1": "763104351884",
"ap-south-2": "772153158452",
"ap-southeast-1": "763104351884",
"ap-southeast-2": "763104351884",
"ap-southeast-3": "907027046896",
"ap-southeast-4": "457447274322",
"ap-southeast-5": "550225433462",
"ap-southeast-6": "633930458069",
"ap-southeast-7": "590183813437",
"ca-central-1": "763104351884",
"ca-west-1": "204538143572",
"cn-north-1": "727897471807",
"cn-northwest-1": "727897471807",
"eu-central-1": "763104351884",
"eu-central-2": "380420809688",
"eu-north-1": "763104351884",
"eu-south-1": "692866216735",
"eu-south-2": "503227376785",
"eu-west-1": "763104351884",
"eu-west-2": "763104351884",
"eu-west-3": "763104351884",
"il-central-1": "780543022126",
"me-central-1": "914824155844",
"me-south-1": "217643126080",
"mx-central-1": "637423239942",
"sa-east-1": "763104351884",
"us-east-1": "763104351884",
"us-east-2": "763104351884",
"us-gov-east-1": "446045086412",
"us-gov-west-1": "442386744353",
"us-iso-east-1": "886529160074",
"us-isob-east-1": "094389454867",
"us-isof-east-1": "303241398832",
"us-isof-south-1": "454834333376",
"us-west-1": "763104351884",
"us-west-2": "763104351884"
},
"tag_prefix": "0.20.0-transformers5.8.1",
"repository": "huggingface-vllm-omni",
"container_version": {
"gpu": "cu130-amzn2023"
}
}
}
}
}
176 changes: 176 additions & 0 deletions sagemaker-core/src/sagemaker/core/image_uri_config/huggingface-vllm.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,176 @@
{
"inference": {
"processors": [
"gpu"
],
"version_aliases": {
"0.14": "0.14.0",
"0.17": "0.17.0",
"0.21": "0.21.0"
},
"versions": {
"0.14.0": {
"py_versions": [
"py312"
],
"registries": {
"af-south-1": "626614931356",
"ap-east-1": "871362719292",
"ap-east-2": "975050140332",
"ap-northeast-1": "763104351884",
"ap-northeast-2": "763104351884",
"ap-northeast-3": "364406365360",
"ap-south-1": "763104351884",
"ap-south-2": "772153158452",
"ap-southeast-1": "763104351884",
"ap-southeast-2": "763104351884",
"ap-southeast-3": "907027046896",
"ap-southeast-4": "457447274322",
"ap-southeast-5": "550225433462",
"ap-southeast-6": "633930458069",
"ap-southeast-7": "590183813437",
"ca-central-1": "763104351884",
"ca-west-1": "204538143572",
"cn-north-1": "727897471807",
"cn-northwest-1": "727897471807",
"eu-central-1": "763104351884",
"eu-central-2": "380420809688",
"eu-north-1": "763104351884",
"eu-south-1": "692866216735",
"eu-south-2": "503227376785",
"eu-west-1": "763104351884",
"eu-west-2": "763104351884",
"eu-west-3": "763104351884",
"il-central-1": "780543022126",
"me-central-1": "914824155844",
"me-south-1": "217643126080",
"mx-central-1": "637423239942",
"sa-east-1": "763104351884",
"us-east-1": "763104351884",
"us-east-2": "763104351884",
"us-gov-east-1": "446045086412",
"us-gov-west-1": "442386744353",
"us-iso-east-1": "886529160074",
"us-isob-east-1": "094389454867",
"us-isof-east-1": "303241398832",
"us-isof-south-1": "454834333376",
"us-west-1": "763104351884",
"us-west-2": "763104351884"
},
"tag_prefix": "0.14.0-transformers4.57.3",
"repository": "huggingface-vllm",
"container_version": {
"gpu": "cu129-ubuntu22.04"
}
},
"0.17.0": {
"py_versions": [
"py312"
],
"registries": {
"af-south-1": "626614931356",
"ap-east-1": "871362719292",
"ap-east-2": "975050140332",
"ap-northeast-1": "763104351884",
"ap-northeast-2": "763104351884",
"ap-northeast-3": "364406365360",
"ap-south-1": "763104351884",
"ap-south-2": "772153158452",
"ap-southeast-1": "763104351884",
"ap-southeast-2": "763104351884",
"ap-southeast-3": "907027046896",
"ap-southeast-4": "457447274322",
"ap-southeast-5": "550225433462",
"ap-southeast-6": "633930458069",
"ap-southeast-7": "590183813437",
"ca-central-1": "763104351884",
"ca-west-1": "204538143572",
"cn-north-1": "727897471807",
"cn-northwest-1": "727897471807",
"eu-central-1": "763104351884",
"eu-central-2": "380420809688",
"eu-north-1": "763104351884",
"eu-south-1": "692866216735",
"eu-south-2": "503227376785",
"eu-west-1": "763104351884",
"eu-west-2": "763104351884",
"eu-west-3": "763104351884",
"il-central-1": "780543022126",
"me-central-1": "914824155844",
"me-south-1": "217643126080",
"mx-central-1": "637423239942",
"sa-east-1": "763104351884",
"us-east-1": "763104351884",
"us-east-2": "763104351884",
"us-gov-east-1": "446045086412",
"us-gov-west-1": "442386744353",
"us-iso-east-1": "886529160074",
"us-isob-east-1": "094389454867",
"us-isof-east-1": "303241398832",
"us-isof-south-1": "454834333376",
"us-west-1": "763104351884",
"us-west-2": "763104351884"
},
"tag_prefix": "0.17.0-transformers4.57.5",
"repository": "huggingface-vllm",
"container_version": {
"gpu": "cu129-ubuntu22.04"
}
},
"0.21.0": {
"py_versions": [
"py312"
],
"registries": {
"af-south-1": "626614931356",
"ap-east-1": "871362719292",
"ap-east-2": "975050140332",
"ap-northeast-1": "763104351884",
"ap-northeast-2": "763104351884",
"ap-northeast-3": "364406365360",
"ap-south-1": "763104351884",
"ap-south-2": "772153158452",
"ap-southeast-1": "763104351884",
"ap-southeast-2": "763104351884",
"ap-southeast-3": "907027046896",
"ap-southeast-4": "457447274322",
"ap-southeast-5": "550225433462",
"ap-southeast-6": "633930458069",
"ap-southeast-7": "590183813437",
"ca-central-1": "763104351884",
"ca-west-1": "204538143572",
"cn-north-1": "727897471807",
"cn-northwest-1": "727897471807",
"eu-central-1": "763104351884",
"eu-central-2": "380420809688",
"eu-north-1": "763104351884",
"eu-south-1": "692866216735",
"eu-south-2": "503227376785",
"eu-west-1": "763104351884",
"eu-west-2": "763104351884",
"eu-west-3": "763104351884",
"il-central-1": "780543022126",
"me-central-1": "914824155844",
"me-south-1": "217643126080",
"mx-central-1": "637423239942",
"sa-east-1": "763104351884",
"us-east-1": "763104351884",
"us-east-2": "763104351884",
"us-gov-east-1": "446045086412",
"us-gov-west-1": "442386744353",
"us-iso-east-1": "886529160074",
"us-isob-east-1": "094389454867",
"us-isof-east-1": "303241398832",
"us-isof-south-1": "454834333376",
"us-west-1": "763104351884",
"us-west-2": "763104351884"
},
"tag_prefix": "0.21.0-transformers5.8.1",
"repository": "huggingface-vllm",
"container_version": {
"gpu": "cu130-ubuntu22.04"
}
}
}
}
}
Loading
Loading