Skip to content

Commit 5015228

Browse files
dacorvodacorvo
authored
Merge branch 'aws:master' into add-neuronx-train-0.0.25
2 parents 0bd3f55 + f97413f commit 5015228

21 files changed

+2260
-93
lines changed

‎available_images.md‎

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -43,6 +43,7 @@ Deep Learning Containers Docker Images are available in the following regions:
4343
| Asia Pacific (Melbourne) | ap-southeast-4 |Available |None | 457447274322.dkr.ecr.ap-southeast-4.amazonaws.com/<repository-name>:<image-tag> |
4444
| Asia Pacific (Tokyo) | ap-northeast-1 |Available |Available | 763104351884.dkr.ecr.ap-northeast-1.amazonaws.com/<repository-name>:<image-tag> |
4545
| Canada (Central) | ca-central-1 |Available |None | 763104351884.dkr.ecr.ca-central-1.amazonaws.com/<repository-name>:<image-tag> |
46+
| Canada (Calgary) | ca-west-1 |Available |None | 204538143572.dkr.ecr.ca-west-1.amazonaws.com/<repository-name>:<image-tag> |
4647
| EU (Frankfurt) | eu-central-1 |Available |Available | 763104351884.dkr.ecr.eu-central-1.amazonaws.com/<repository-name>:<image-tag> |
4748
| EU (Zurich) | eu-central-2 |Available |None | 380420809688.dkr.ecr.eu-central-2.amazonaws.com/<repository-name>:<image-tag> |
4849
| EU (Ireland) | eu-west-1 |Available |Available | 763104351884.dkr.ecr.eu-west-1.amazonaws.com/<repository-name>:<image-tag> |
@@ -184,14 +185,14 @@ Starting LMI V10 (0.28.0), we are changing the name from LMI DeepSpeed DLC to LM
184185

185186
| Framework | Job Type | Accelerator | Python Version Options | Example URL |
186187
|------------------------------------------------------------------------------------------------------------------------------|-----------|-------------|------------------------|-------------------------------------------------------------------------------------------|
188+
| DJLServing 0.30.0 with LMI Dist 12.0.0, vLLM 0.6.2, HuggingFace Transformers 4.45.2, and HuggingFace Accelerate 1.0.1 | inference | GPU | 3.10 (py310) | 763104351884.dkr.ecr.us-west-2.amazonaws.com/djl-inference:0.30.0-lmi12.0.0-cu124 |
187189
| DJLServing 0.29.0 with TensorRT-LLM 0.11.0, HuggingFace Transformers 4.42.4, and HuggingFace Accelerate 0.32.1 | inference | GPU | 3.10 (py310) | 763104351884.dkr.ecr.us-west-2.amazonaws.com/djl-inference:0.29.0-tensorrtllm0.11.0-cu124 |
188190
| DJLServing 0.29.0 with LMI Dist 11.0.0, HuggingFace Transformers 4.43.2, HuggingFace Accelerate 0.32.1 | inference | GPU | 3.10 (py310) | 763104351884.dkr.ecr.us-west-2.amazonaws.com/djl-inference:0.29.0-lmi11.0.0-cu124 |
189191
| DJLServing 0.29.0 with Neuron SDK 2.19.1, TransformersNeuronX 0.11.351 and HuggingFace Transformers 4.43.1 | inference | Neuron | 3.10 (py310) | 763104351884.dkr.ecr.us-west-2.amazonaws.com/djl-inference:0.29.0-neuronx-sdk2.19.1 |
190192
| DJLServing 0.28.0 with TensorRT-LLM 0.9.0, HuggingFace Transformers 4.40.0, and HuggingFace Accelerate 0.29.3 | inference | GPU | 3.10 (py310) | 763104351884.dkr.ecr.us-west-2.amazonaws.com/djl-inference:0.28.0-tensorrtllm0.9.0-cu122 |
191193
| DJLServing 0.28.0 with LMI Dist 0.10.0, HuggingFace Transformers 4.41.1, HuggingFace Accelerate 0.30.1 | inference | GPU | 3.10 (py310) | 763104351884.dkr.ecr.us-west-2.amazonaws.com/djl-inference:0.28.0-lmi10.0.0-cu124 |
192194
| DJLServing 0.28.0 with Neuron SDK 2.18.2, TransformersNeuronX 0.10.0.360 and HuggingFace Transformers 4.36.2 | inference | Neuron | 3.10 (py310) | 763104351884.dkr.ecr.us-west-2.amazonaws.com/djl-inference:0.28.0-neuronx-sdk2.18.2 |
193195
| DJLServing 0.27.0 with TensorRT-LLM 0.8.0, HuggingFace Transformers 4.38.1, and HuggingFace Accelerate 0.27.0 | inference | GPU | 3.10 (py310) | 763104351884.dkr.ecr.us-west-2.amazonaws.com/djl-inference:0.27.0-tensorrtllm0.8.0-cu122 |
194-
| DJLServing 0.27.0 with DeepSpeed 0.12.6, HuggingFace Transformers 4.39.0, Diffusers 0.16.0 and HuggingFace Accelerate 0.28.0 | inference | GPU | 3.10 (py310) | 763104351884.dkr.ecr.us-west-2.amazonaws.com/djl-inference:0.27.0-deepspeed0.12.6-cu121 |
195196
| DJLServing 0.27.0 with Neuron SDK 2.18.1, TransformersNeuronX 0.10.0.360 and HuggingFace Transformers 4.36.2 | inference | Neuron | 3.9 (py39) | 763104351884.dkr.ecr.us-west-2.amazonaws.com/djl-inference:0.27.0-neuronx-sdk2.18.1 |
196197

197198
DJL CPU Full Inference Containers

‎pytorch/inference/buildspec-2-4-ec2.yml‎

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -5,7 +5,7 @@ framework: &FRAMEWORK pytorch
55
version: &VERSION 2.4.0
66
short_version: &SHORT_VERSION "2.4"
77
arch_type: x86
8-
autopatch_build: "True"
8+
# autopatch_build: "True"
99

1010
repository_info:
1111
inference_repository: &INFERENCE_REPOSITORY
@@ -40,7 +40,7 @@ images:
4040
python_version: &DOCKER_PYTHON_VERSION py3
4141
tag_python_version: &TAG_PYTHON_VERSION py311
4242
os_version: &OS_VERSION ubuntu22.04
43-
torch_serve_version: &TORCHSERVE_VERSION 0.11.1
43+
torch_serve_version: &TORCHSERVE_VERSION 0.12.0
4444
tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *OS_VERSION, "-ec2" ]
4545
latest_release_tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *OS_VERSION, "-ec2" ]
4646
# build_tag_override: "beta:2.4.0-cpu-py311-ubuntu22.04-ec2"
@@ -57,7 +57,7 @@ images:
5757
tag_python_version: &TAG_PYTHON_VERSION py311
5858
cuda_version: &CUDA_VERSION cu124
5959
os_version: &OS_VERSION ubuntu22.04
60-
torch_serve_version: &TORCHSERVE_VERSION 0.11.1
60+
torch_serve_version: &TORCHSERVE_VERSION 0.12.0
6161
tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *CUDA_VERSION, "-", *OS_VERSION, "-ec2" ]
6262
latest_release_tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *CUDA_VERSION, "-", *OS_VERSION, "-ec2" ]
6363
# build_tag_override: "beta:2.4.0-gpu-py311-cu124-ubuntu22.04-ec2"

‎pytorch/inference/buildspec-graviton-2-4-ec2.yml‎

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -5,7 +5,7 @@ framework: &FRAMEWORK pytorch
55
version: &VERSION 2.4.0
66
short_version: &SHORT_VERSION "2.4"
77
arch_type: graviton
8-
autopatch_build: "True"
8+
# autopatch_build: "True"
99

1010
repository_info:
1111
inference_repository: &INFERENCE_REPOSITORY
@@ -40,7 +40,7 @@ images:
4040
python_version: &DOCKER_PYTHON_VERSION py3
4141
tag_python_version: &TAG_PYTHON_VERSION py311
4242
os_version: &OS_VERSION ubuntu22.04
43-
torch_serve_version: &TORCHSERVE_VERSION 0.11.1
43+
torch_serve_version: &TORCHSERVE_VERSION 0.12.0
4444
tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *OS_VERSION , "-ec2"]
4545
latest_release_tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *OS_VERSION, "-ec2" ]
4646
# build_tag_override: "beta:2.4.0-cpu-py311-ubuntu22.04-ec2"
@@ -57,7 +57,7 @@ images:
5757
tag_python_version: &TAG_PYTHON_VERSION py311
5858
cuda_version: &CUDA_VERSION cu124
5959
os_version: &OS_VERSION ubuntu22.04
60-
torch_serve_version: &TORCHSERVE_VERSION 0.11.1
60+
torch_serve_version: &TORCHSERVE_VERSION 0.12.0
6161
tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *CUDA_VERSION, "-", *OS_VERSION , "-ec2"]
6262
latest_release_tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *CUDA_VERSION, "-", *OS_VERSION, "-ec2" ]
6363
# build_tag_override: "beta:2.4.0-gpu-py311-cu124-ubuntu22.04-ec2"

0 commit comments

Comments
 (0)