inference-nv-pytorch 26.02 Release Notes | ACS - Container Compute Service

Release notes for the inference-nv-pytorch 26.02 container image.

Main features and bug fixes

Main features

Images are available for CUDA 12.8 and CUDA 13.0:
- The CUDA 12.8 images support only the amd64 architecture.
- The CUDA 13.0 images support both the amd64 and aarch64 architectures.
vLLM images: Torch upgraded to 2.10.0, vLLM to v0.15.1.
SGLang images: Torch upgraded to 2.10.0, SGLang to v0.5.9.

Bug fixes

None.

Image specifications

Image	inference-nv-pytorch
Tag	26.02-vllm0.15.1-pytorch2.10-cu128-20260211-serverless	26.02-sglang0.5.9-pytorch2.10-cu128-20260227-serverless	26.02-vllm0.15.1-pytorch2.10-cu130-20260211-serverless		26.02-sglang0.5.9-pytorch2.10-cu130-20260227-serverless
Architecture	amd64	amd64	amd64	aarch64	amd64	aarch64
Use case	large model inference	large model inference	large model inference	large model inference	large model inference	large model inference
Framework	pytorch	pytorch	pytorch	pytorch	pytorch	pytorch
Requirements	NVIDIA Driver release >= 570	NVIDIA Driver release >= 570	NVIDIA Driver release >= 580	NVIDIA Driver release >= 580	NVIDIA Driver release >= 580	NVIDIA Driver release >= 580
System components	Ubuntu 24.04 Python 3.12 Torch 2.10.0 CUDA 12.8 NCCL 2.28.9 diffusers 0.36.0 flash_attn 2.8.3 flash_attn_3 3.0.0 flashinfer-python 0.6.1 imageio 2.37.2 imageio-ffmpeg 0.6.0 ray 2.53.0 transformers 4.57.6 triton 3.6.0 torchaudio 2.10.0 torchvision 0.25.0 vllm 0.15.1 xfuser 0.4.5 xgrammar 0.1.27 ljperf 0.1.0+477686c5	Ubuntu 24.04 Python 3.12 Torch 2.10.0 CUDA 12.8 NCCL 2.28.9 torchaudio 2.10.0 torchvision 0.25.0 diffusers 0.36.0 decord 0.6.0 decord2 3.0.0 flash_attn 2.8.3 flash_attn_3 3.0.0 flashinfer-python 0.6.3 imageio 2.37.2 imageio-ffmpeg 0.6.0 ray 2.54.0 transformers 4.57.1 sgl-kernel 0.3.21 sglang 0.5.9 xgrammar 0.1.27 triton 3.6.0 torchao 0.9.0 xfuser 0.4.5 ljperf 0.1.0+477686c5	Ubuntu 24.04 Python 3.12 Torch 2.10.0+cu130 CUDA 13.0.2 NCCL 2.28.9 diffusers 0.36.0 flash_attn 2.8.3 flash_attn_3 3.0.0 flashinfer-python 0.6.1 imageio 2.37.2 imageio-ffmpeg 0.6.0 ray 2.53.0 transformers 4.57.6 triton 3.6.0 torchaudio 2.10.0+cu130 torchvision 0.25.0+cu130 vllm 0.15.1 xfuser 0.4.5 xgrammar 0.1.27 ljperf 0.1.0+d0e4a408	Ubuntu 24.04 Python 3.12 Torch 2.10.0+cu130 CUDA 13.0.2 NCCL 2.28.9 diffusers 0.36.0 flash_attn 2.8.3 flashinfer-python 0.6.1 transformers 4.57.6 ray 2.53.0 vllm 0.15.1 triton 3.6.0 torchaudio 2.10.0+cu130 torchvision 2.10.0+cu130 xfuser 0.4.5 xgrammar 0.1.27 ljperf 0.1.0+477686c5	Ubuntu 24.04 Python 3.12 Torch 2.10.0+cu130 CUDA 13.0.2 NCCL 2.28.9 diffusers 0.36.0 decord 0.6.0 decord2 3.0.0 flash_attn 2.8.3 flashinfer-python 0.6.3 imageio 2.37.2 imageio-ffmpeg 0.6.0 ray 2.54.0 transformers 4.57.1 sgl-kernel 0.3.21 sglang 0.5.9 xgrammar 0.1.27 triton 3.6.0 torchao 0.9.0 torchaudio 2.10.0+cu130 torchvision 0.25.0+cu130 xfuser 0.4.5 ljperf 0.1.0+d0e4a408	Ubuntu 24.04 Python 3.12 Torch 2.10.0+cu130 CUDA 13.0.2 NCCL 2.28.9 diffusers 0.36.0 decord2 3.0.0 flash_attn 2.8.3 flashinfer-python 0.6.3 imageio 2.37.2 imageio-ffmpeg 0.6.0 ray 2.54.0 transformers 4.57.1 sgl-kernel 0.3.21 sglang 0.5.9 xgrammar 0.1.27 triton 3.6.0 torchao 0.9.0 torchaudio 2.10.0+cu130 torchvision 0.25.0+cu130 xfuser 0.4.5 ljperf 0.1.0+477686c5

Assets

Public images

CUDA 12.8 assets

egslingjun-registry.cn-wulanchabu.cr.aliyuncs.com/egslingjun/inference-nv-pytorch:26.02-vllm0.15.1-pytorch2.10-cu128-20260211-serverless
egslingjun-registry.cn-wulanchabu.cr.aliyuncs.com/egslingjun/inference-nv-pytorch:26.02-sglang0.5.9-pytorch2.10-cu128-20260227-serverless

CUDA 13.0 assets

egslingjun-registry.cn-wulanchabu.cr.aliyuncs.com/egslingjun/inference-nv-pytorch:26.02-vllm0.15.1-pytorch2.10-cu130-20260211-serverless
egslingjun-registry.cn-wulanchabu.cr.aliyuncs.com/egslingjun/inference-nv-pytorch:26.02-sglang0.5.9-pytorch2.10-cu130-20260227-serverless

VPC images

All existing and new ACS AI container images in the egslingjun-registry.cn-wulanchabu.cr.aliyuncs.com/egslingjun repository support IN-VPC pulling.

Replace the public network registry host in your image URI with the region-specific VPC endpoint.

URI component	Public network	IN-VPC
Registry host	`egslingjun-registry.cn-wulanchabu.cr.aliyuncs.com`	`acs-registry-vpc.{region-id}.cr.aliyuncs.com`
Repository	`egslingjun`	`egslingjun` (unchanged)
Image and tag	`{image:tag}`	`{image:tag}` (unchanged)

Replace {region-id} with the ID of the region where your ACS service runs. For example:

Region	Region ID
China (Beijing)	`cn-beijing`
China (Ulanqab)	`cn-wulanchabu`

For the full list of supported regions, see Regions.

Example {image:tag} values:

inference-nv-pytorch:25.10-vllm0.11.0-pytorch2.8-cu128-20251028-serverless
training-nv-pytorch:25.10-serverless

Note

These images are for ACS and the Lingjun multi-tenant offering. Do not use them in Lingjun single-tenant scenarios.

Driver requirements

CUDA 12.8: NVIDIA Driver release >= 570
CUDA 13.0: NVIDIA Driver release >= 580

Quick start

Pull the inference-nv-pytorch image with Docker and test inference with the Qwen2.5-7B-Instruct model.

Note

To use this image in ACS, select it from the Artifacts Center on the Create Workload page in the console, or specify the image reference in a YAML file. Related guides for building model inference services with ACS GPU compute:

Pull the inference container image.

docker pull egslingjun-registry.cn-wulanchabu.cr.aliyuncs.com/egslingjun/inference-nv-pytorch:[tag]

Use ModelScope to download the open-source model.

pip install modelscope
cd /mnt
modelscope download --model Qwen/Qwen2.5-7B-Instruct --local_dir ./Qwen2.5-7B-Instruct

Enter the container.

docker run -it --rm --gpus all --network=host --privileged --init --ipc=host \
--ulimit memlock=-1 --ulimit stack=67108864  \
-v /mnt/:/mnt/ \
egslingjun-registry.cn-wulanchabu.cr.aliyuncs.com/egslingjun/inference-nv-pytorch:[tag]

Test the vLLM chat feature.

Start the server.

python3 -m vllm.entrypoints.openai.api_server \
--model /mnt/Qwen2.5-7B-Instruct \
--trust-remote-code --disable-custom-all-reduce \
--tensor-parallel-size 1

Run a client-side test.

curl http://localhost:8000/v1/chat/completions \
    -H "Content-Type: application/json" \
    -d '{
    "model": "/mnt/Qwen2.5-7B-Instruct",  
    "messages": [
    {"role": "system", "content": "You are a friendly AI assistant."},
    {"role": "user", "content": "Introduce deep learning."}
    ]}'

The vLLM documentation covers additional configuration options.

Known issues

In this release, these images do not support the deepgpu-comfyui plugin.