Please visit Deep Learning Framework (DLFW) website for the complete compatibility matrix.

Release Compatibility Matrix#

Container Name: trtllm-python-py3#

Triton release version

NGC Tag

Python version

Torch version

TensorRT version

TensorRT-LLM version

CUDA version

CUDA Driver version

Size

25.04

nvcr.io/nvidia/tritonserver:25.04-trtllm-python-py3

Python 3.12.3

2.7.0a0+7c8ec84dab.nv25.3

10.9.0.34

0.18.2

12.8.1.012

570.124.06

17G

25.03

nvcr.io/nvidia/tritonserver:25.03-trtllm-python-py3

Python 3.12.3

2.7.0a0%2B7c8ec84dab.nv25.3

10.9.0.34

0.18.0

12.8.1.012

570.124.06

28G

25.02

nvcr.io/nvidia/tritonserver:25.02-trtllm-python-py3

Python 3.12.3

2.6.0a0%2Becf3bae40a.nv25.1

10.8.0.43

0.17.0.post1

12.8.0.038

570.86.10

28G

25.01

nvcr.io/nvidia/tritonserver:25.01-trtllm-python-py3

Python 3.12.3

2.6.0a0%2Becf3bae40a.nv25.1

10.8.0.43

0.17.0

12.8.0.038

570.86.10

30G

24.12

nvcr.io/nvidia/tritonserver:24.12-trtllm-python-py3

Python 3.12.3

2.6.0a0%2Bdf5bbc09d1.nv24.11

10.7.0

0.16.0

12.6.3

560.35.05

22G

24.11

nvcr.io/nvidia/tritonserver:24.11-trtllm-python-py3

Python 3.10.12

2.5.0a0%2Be000cf0ad9.nv24.10

10.6.0

0.15.0

12.6.3

555.42.06

24.8G

24.10

nvcr.io/nvidia/tritonserver:24.10-trtllm-python-py3

Python 3.10.12

2.4.0a0%2B3bcc3cddb5.nv24.7

10.4.0

0.14.0

12.5.1.007

555.42.06

23.3G

24.09

nvcr.io/nvidia/tritonserver:24.09-trtllm-python-py3

Python 3.10.12

2.4.0a0%2B3bcc3cddb5.nv24.7

10.4.0

0.13.0

12.5.1.007

555.42.06

21G

24.08

nvcr.io/nvidia/tritonserver:24.08-trtllm-python-py3

Python 3.10.12

2.4.0a0%2B3bcc3cddb5.nv24.7

10.3.0

0.12.0

12.5.1.007

555.42.06

21G

24.07

nvcr.io/nvidia/tritonserver:24.07-trtllm-python-py3

Python 3.10.12

2.4.0a0%2B07cecf4168.nv24.5

10.1.0

0.11.0

12.4.1.003

550.54.15

23G

24.06

nvcr.io/nvidia/tritonserver:24.06-trtllm-python-py3

Python 3.10.12

2.3.0a0%2B40ec155e58.nv24.3

10.0.1

0.10.0

12.4.0.041

550.54.14

31G

24.05

nvcr.io/nvidia/tritonserver:24.05-trtllm-python-py3

Python 3.10.12

2.3.0a0%2Bebedce2

10.0.1.6

0.9.0

12.3.2.001

545.23.08

34G

24.04

nvcr.io/nvidia/tritonserver:24.04-trtllm-python-py3

Python 3.10.12

2.3.0a0%2Bebedce2

9.3.0.post12.dev1

0.9.0

12.3.2.001

545.23.08

34G

Container Name: vllm-python-py3#

Triton release version

NGC Tag

Python version

vLLM version

CUDA version

CUDA Driver version

Size

25.04

nvcr.io/nvidia/tritonserver:25.04-vllm-python-py3

Python 3.12.3

0.8.1+5f4af9e0.nv25.4.cu129

12.9.0.036

575.51.02

10G

25.03

nvcr.io/nvidia/tritonserver:25.03-vllm-python-py3

Python 3.12.3

0.7.3+04de634a.nv25.3.cu128

12.8.1.012

570.124.06

22G

25.02

nvcr.io/nvidia/tritonserver:25.02-vllm-python-py3

Python 3.12.3

0.7.0+5e800e3d.nv25.2.cu128

12.8.0.038

570.86.10

22G

25.01

nvcr.io/nvidia/tritonserver:25.01-vllm-python-py3

Python 3.12.3

0.6.3.post1

12.8.0.038

570.86.10

23G

24.12

nvcr.io/nvidia/tritonserver:24.12-vllm-python-py3

Python 3.12.3

0.5.5

12.6.3.004

560.35.05

20G

24.11

nvcr.io/nvidia/tritonserver:24.11-vllm-python-py3

Python 3.12.3

0.5.5

12.6.3.001

560.35.05

22.1G

24.10

nvcr.io/nvidia/tritonserver:24.10-vllm-python-py3

Python 3.10.12

0.5.5

12.6.2.004

560.35.03

21G

24.09

nvcr.io/nvidia/tritonserver:24.09-vllm-python-py3

Python 3.10.12

0.5.3.post1

12.6.1.006

560.35.03

19G

24.08

nvcr.io/nvidia/tritonserver:24.08-vllm-python-py3

Python 3.10.12

0.5.0 post1

12.6.0.022

560.35.03

19G

24.07

nvcr.io/nvidia/tritonserver:24.07-vllm-python-py3

Python 3.10.12

0.5.0 post1

12.5.1

555.42.06

19G

24.06

nvcr.io/nvidia/tritonserver:24.06-vllm-python-py3

Python 3.10.12

0.4.3

12.5.0.23

555.42.02

18G

24.05

nvcr.io/nvidia/tritonserver:24.05-vllm-python-py3

Python 3.10.12

0.4.0 post1

12.4.1

550.54.15

18G

24.04

nvcr.io/nvidia/tritonserver:24.04-vllm-python-py3

Python 3.10.12

0.4.0 post1

12.4.1

550.54.15

17G

ONNX Runtime Versions#

Triton release version

ONNX Runtime

25.04

1.21.0

25.03

1.21.0

25.02

1.20.1

25.01

1.20.1

24.12

1.20.1

24.11

1.19.2

24.10

1.19.2

24.09

1.19.2

24.08

1.18.1

24.07

1.18.1

24.06

1.18.0

24.05

1.18.0

24.04

1.17.3