Skip to content

tgi optimum 0.0.18 (general+llm) #4436

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

Merged
merged 11 commits into from
Feb 27, 2024
Merged

tgi optimum 0.0.18 (general+llm) #4436

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
c3c56c6
tgi optimum 0.0.18
jinyoung-lim Feb 19, 2024
3d750e1
add test
jinyoung-lim Feb 19, 2024
ebfa454
Merge branch 'master' into tgi-optimum-0.0.18
jinyoung-lim Feb 19, 2024
ac07b93
update latest transformer version
jinyoung-lim Feb 20, 2024
a8dbcef
add dlc optimum 0.0.18 config
jinyoung-lim Feb 20, 2024
e82b4be
0.0 defaults to 0.0.16
jinyoung-lim Feb 21, 2024
f9d53a0
Merge branch 'master' into tgi-optimum-0.0.18
jinyoung-lim Feb 22, 2024
7ba36b7
Merge branch 'master' into tgi-optimum-0.0.18
jinyoung-lim Feb 23, 2024
ea78de6
Merge branch 'master' into tgi-optimum-0.0.18
jinyoung-lim Feb 26, 2024
6dd7d59
Merge branch 'master' into tgi-optimum-0.0.18
jinyoung-lim Feb 26, 2024
d6e14ff
Merge branch 'master' into tgi-optimum-0.0.18
jinyoung-lim Feb 27, 2024
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
29 changes: 29 additions & 0 deletions src/sagemaker/image_uri_config/huggingface-llm-neuronx.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -64,6 +64,35 @@
"container_version": {
"inf2": "ubuntu22.04"
}
},
"0.0.18": {
"py_versions": [
"py310"
],
"registries": {
"ap-northeast-1": "763104351884",
"ap-south-1": "763104351884",
"ap-south-2": "772153158452",
"ap-southeast-1": "763104351884",
"ap-southeast-2": "763104351884",
"ap-southeast-4": "457447274322",
"eu-central-1": "763104351884",
"eu-central-2": "380420809688",
"eu-south-2": "503227376785",
"eu-west-1": "763104351884",
"eu-west-3": "763104351884",
"il-central-1": "780543022126",
"sa-east-1": "763104351884",
"us-east-1": "763104351884",
"us-east-2": "763104351884",
"us-west-2": "763104351884",
"ca-west-1": "204538143572"
},
"tag_prefix": "1.13.1-optimum0.0.18",
"repository": "huggingface-pytorch-tgi-inference",
"container_version": {
"inf2": "ubuntu22.04"
}
}
}
}
Expand Down
59 changes: 57 additions & 2 deletions src/sagemaker/image_uri_config/huggingface-neuronx.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,8 @@
"trn"
],
"version_aliases": {
"4.28": "4.28.1"
"4.28": "4.28.1",
"4.34": "4.34.1"
},
"versions": {
"4.28.1": {
Expand Down Expand Up @@ -86,7 +87,9 @@
"inf"
],
"version_aliases": {
"4.28": "4.28.1"
"4.28": "4.28.1",
"4.34": "4.34.1",
"4.36": "4.36.2"
},
"versions": {
"4.28.1": {
Expand Down Expand Up @@ -192,6 +195,58 @@
"sdk2.15.0"
]
}
},
"4.36.2": {
"version_aliases": {
"pytorch1.13": "pytorch1.13.1"
},
"pytorch1.13.1": {
"py_versions": [
"py310"
],
"repository": "huggingface-pytorch-inference-neuronx",
"registries": {
"af-south-1": "626614931356",
"il-central-1": "780543022126",
"ap-east-1": "871362719292",
"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-4": "457447274322",
"ca-central-1": "763104351884",
"cn-north-1": "727897471807",
"cn-northwest-1": "727897471807",
"eu-central-1": "763104351884",
"eu-central-2": "380420809688",
"eu-north-1": "763104351884",
"eu-west-1": "763104351884",
"eu-west-2": "763104351884",
"eu-west-3": "763104351884",
"eu-south-1": "692866216735",
"eu-south-2": "503227376785",
"me-south-1": "217643126080",
"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-west-1": "763104351884",
"us-west-2": "763104351884",
"ca-west-1": "204538143572"
},
"container_version": {
"inf": "ubuntu20.04"
},
"sdk_versions": [
"sdk2.16.1"
]
}
}
}
}
Expand Down
2 changes: 1 addition & 1 deletion tests/conftest.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -441,7 +441,7 @@ def huggingface_neuron_latest_inference_transformer_version():

@pytest.fixture(scope="module")
def huggingface_neuronx_latest_inference_transformer_version():
return "4.34.1"
return "4.36.2"


@pytest.fixture(scope="module")
Expand Down
1 change: 1 addition & 0 deletions tests/unit/sagemaker/image_uris/test_huggingface_llm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,6 +33,7 @@
"inf2": {
"0.0.16": "1.13.1-optimum0.0.16-neuronx-py310-ubuntu22.04",
"0.0.17": "1.13.1-optimum0.0.17-neuronx-py310-ubuntu22.04",
"0.0.18": "1.13.1-optimum0.0.18-neuronx-py310-ubuntu22.04",
},
}

Expand Down