Skip to content

Releases: EmbeddedLLM/vllm-rocm

ROCm Wheels - 2025-11-21

21 Nov 13:25
@github-actions github-actions
wheels-20251121-132538
035f0f1

Choose a tag to compare

View all tags
ROCm Wheels - 2025-11-21 Latest
Latest

Large ML framework wheels for vLLM ROCm

Included Wheels

cupy_cuda12x-13.6.0-cp312-cp312-manylinux2014_x86_64.whl
nvidia_cublas_cu12-12.8.4.1-py3-none-manylinux_2_27_x86_64.whl
nvidia_cudnn_cu12-9.10.2.21-py3-none-manylinux_2_27_x86_64.whl
nvidia_cufft_cu12-11.3.3.83-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl
nvidia_cusolver_cu12-11.7.3.90-py3-none-manylinux_2_27_x86_64.whl
nvidia_cusparse_cu12-12.5.8.93-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl
nvidia_cusparselt_cu12-0.7.1-py3-none-manylinux2014_x86_64.whl
nvidia_nccl_cu12-2.27.5-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl
nvidia_nvshmem_cu12-3.3.20-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl
torch-2.9.0a0+git1c57644-cp312-cp312-linux_x86_64.whl
torch-2.9.1-cp312-cp312-manylinux_2_28_x86_64.whl
triton-3.4.0-cp312-cp312-linux_x86_64.whl
triton-3.5.1-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl

Build Info

  • ROCm Version: 7.1
  • Python Version: 3.12
  • GPU Architectures: gfx942
  • Commit: 035f0f1

Installation

These wheels are automatically referenced by the PyPI index at:
https://EmbeddedLLM.github.io/vllm-rocm/simple/

Use: pip install vllm-rocm --index-url https://EmbeddedLLM.github.io/vllm-rocm/simple/

Assets 15

ROCm Wheels - 2025-11-21

21 Nov 11:42
@github-actions github-actions
wheels-20251121-114243
7318db8

Choose a tag to compare

View all tags
ROCm Wheels - 2025-11-21

Large ML framework wheels for vLLM ROCm

Included Wheels

cupy_cuda12x-13.6.0-cp312-cp312-manylinux2014_x86_64.whl
nvidia_cublas_cu12-12.8.4.1-py3-none-manylinux_2_27_x86_64.whl
nvidia_cudnn_cu12-9.10.2.21-py3-none-manylinux_2_27_x86_64.whl
nvidia_cufft_cu12-11.3.3.83-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl
nvidia_cusolver_cu12-11.7.3.90-py3-none-manylinux_2_27_x86_64.whl
nvidia_cusparse_cu12-12.5.8.93-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl
nvidia_cusparselt_cu12-0.7.1-py3-none-manylinux2014_x86_64.whl
nvidia_nccl_cu12-2.27.5-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl
nvidia_nvshmem_cu12-3.3.20-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl
torch-2.9.0a0+git1c57644-cp312-cp312-linux_x86_64.whl
torch-2.9.1-cp312-cp312-manylinux_2_28_x86_64.whl
triton-3.4.0-cp312-cp312-linux_x86_64.whl
triton-3.5.1-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl

Build Info

  • ROCm Version: 7.1
  • Python Version: 3.12
  • GPU Architectures: gfx942
  • Commit: 7318db8

Installation

These wheels are automatically referenced by the PyPI index at:
https://EmbeddedLLM.github.io/vllm-rocm/simple/

Use: pip install vllm-rocm --index-url https://EmbeddedLLM.github.io/vllm-rocm/simple/

Loading

ROCm Wheels - 2025-11-21

21 Nov 11:24
@github-actions github-actions
wheels-20251121-112356
a98d10f

Choose a tag to compare

View all tags
ROCm Wheels - 2025-11-21

Large ML framework wheels for vLLM ROCm

Included Wheels

cupy_cuda12x-13.6.0-cp312-cp312-manylinux2014_x86_64.whl
nvidia_cublas_cu12-12.8.4.1-py3-none-manylinux_2_27_x86_64.whl
nvidia_cudnn_cu12-9.10.2.21-py3-none-manylinux_2_27_x86_64.whl
nvidia_cufft_cu12-11.3.3.83-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl
nvidia_cusolver_cu12-11.7.3.90-py3-none-manylinux_2_27_x86_64.whl
nvidia_cusparse_cu12-12.5.8.93-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl
nvidia_cusparselt_cu12-0.7.1-py3-none-manylinux2014_x86_64.whl
nvidia_nccl_cu12-2.27.5-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl
nvidia_nvshmem_cu12-3.3.20-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl
torch-2.9.0a0+git1c57644-cp312-cp312-linux_x86_64.whl
torch-2.9.1-cp312-cp312-manylinux_2_28_x86_64.whl
triton-3.4.0-cp312-cp312-linux_x86_64.whl
triton-3.5.1-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl

Build Info

  • ROCm Version: 7.1
  • Python Version: 3.12
  • GPU Architectures: gfx942
  • Commit: a98d10f

Installation

These wheels are automatically referenced by the PyPI index at:
https://EmbeddedLLM.github.io/vllm-rocm/simple/

Use: pip install vllm-rocm --index-url https://EmbeddedLLM.github.io/vllm-rocm/simple/

Loading

ROCm Wheels - 2025-11-21

21 Nov 11:10
@github-actions github-actions
wheels-20251121-111002
0a8bd9f

Choose a tag to compare

View all tags
ROCm Wheels - 2025-11-21

Large ML framework wheels for vLLM ROCm

Included Wheels

cupy_cuda12x-13.6.0-cp312-cp312-manylinux2014_x86_64.whl
nvidia_cublas_cu12-12.8.4.1-py3-none-manylinux_2_27_x86_64.whl
nvidia_cudnn_cu12-9.10.2.21-py3-none-manylinux_2_27_x86_64.whl
nvidia_cufft_cu12-11.3.3.83-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl
nvidia_cusolver_cu12-11.7.3.90-py3-none-manylinux_2_27_x86_64.whl
nvidia_cusparse_cu12-12.5.8.93-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl
nvidia_cusparselt_cu12-0.7.1-py3-none-manylinux2014_x86_64.whl
nvidia_nccl_cu12-2.27.5-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl
nvidia_nvshmem_cu12-3.3.20-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl
torch-2.9.0a0+git1c57644-cp312-cp312-linux_x86_64.whl
torch-2.9.1-cp312-cp312-manylinux_2_28_x86_64.whl
triton-3.4.0-cp312-cp312-linux_x86_64.whl
triton-3.5.1-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl

Build Info

  • ROCm Version: 7.1
  • Python Version: 3.12
  • GPU Architectures: gfx942
  • Commit: 0a8bd9f

Installation

These wheels are automatically referenced by the PyPI index at:
https://EmbeddedLLM.github.io/vllm-rocm/simple/

Use: pip install vllm-rocm --index-url https://EmbeddedLLM.github.io/vllm-rocm/simple/

Loading

ROCm Wheels - 2025-11-21

21 Nov 10:57
@github-actions github-actions
wheels-20251121-105719
dea8943

Choose a tag to compare

View all tags
ROCm Wheels - 2025-11-21

Large ML framework wheels for vLLM ROCm

Included Wheels

cupy_cuda12x-13.6.0-cp312-cp312-manylinux2014_x86_64.whl
nvidia_cublas_cu12-12.8.4.1-py3-none-manylinux_2_27_x86_64.whl
nvidia_cudnn_cu12-9.10.2.21-py3-none-manylinux_2_27_x86_64.whl
nvidia_cufft_cu12-11.3.3.83-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl
nvidia_cusolver_cu12-11.7.3.90-py3-none-manylinux_2_27_x86_64.whl
nvidia_cusparse_cu12-12.5.8.93-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl
nvidia_cusparselt_cu12-0.7.1-py3-none-manylinux2014_x86_64.whl
nvidia_nccl_cu12-2.27.5-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl
nvidia_nvshmem_cu12-3.3.20-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl
torch-2.9.0a0+git1c57644-cp312-cp312-linux_x86_64.whl
torch-2.9.1-cp312-cp312-manylinux_2_28_x86_64.whl
triton-3.4.0-cp312-cp312-linux_x86_64.whl
triton-3.5.1-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl

Build Info

  • ROCm Version: 7.1
  • Python Version: 3.12
  • GPU Architectures: gfx942
  • Commit: dea8943

Installation

These wheels are automatically referenced by the PyPI index at:
https://EmbeddedLLM.github.io/vllm-rocm/simple/

Use: pip install vllm-rocm --index-url https://EmbeddedLLM.github.io/vllm-rocm/simple/

Loading

ROCm Wheels - 2025-11-21

21 Nov 10:45
@github-actions github-actions
wheels-20251121-104533
dea8943

Choose a tag to compare

View all tags
ROCm Wheels - 2025-11-21

Large ML framework wheels for vLLM ROCm

Included Wheels

cupy_cuda12x-13.6.0-cp312-cp312-manylinux2014_x86_64.whl
nvidia_cublas_cu12-12.8.4.1-py3-none-manylinux_2_27_x86_64.whl
nvidia_cudnn_cu12-9.10.2.21-py3-none-manylinux_2_27_x86_64.whl
nvidia_cufft_cu12-11.3.3.83-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl
nvidia_cusolver_cu12-11.7.3.90-py3-none-manylinux_2_27_x86_64.whl
nvidia_cusparse_cu12-12.5.8.93-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl
nvidia_cusparselt_cu12-0.7.1-py3-none-manylinux2014_x86_64.whl
nvidia_nccl_cu12-2.27.5-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl
nvidia_nvshmem_cu12-3.3.20-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl
torch-2.9.0a0+git1c57644-cp312-cp312-linux_x86_64.whl
torch-2.9.1-cp312-cp312-manylinux_2_28_x86_64.whl
triton-3.4.0-cp312-cp312-linux_x86_64.whl
triton-3.5.1-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl

Build Info

  • ROCm Version: 7.1
  • Python Version: 3.12
  • GPU Architectures: gfx942
  • Commit: 035f0f1

Installation

These wheels are automatically referenced by the PyPI index at:
https://EmbeddedLLM.github.io/vllm-rocm/simple/

Use: pip install vllm-rocm --index-url https://EmbeddedLLM.github.io/vllm-rocm/simple/

Loading

ROCm Wheels - 2025-11-21

21 Nov 09:26
@github-actions github-actions
wheels-20251121-092641
035f0f1

Choose a tag to compare

View all tags
ROCm Wheels - 2025-11-21

Large ML framework wheels for vLLM ROCm

Included Wheels

cupy_cuda12x-13.6.0-cp312-cp312-manylinux2014_x86_64.whl
nvidia_cublas_cu12-12.8.4.1-py3-none-manylinux_2_27_x86_64.whl
nvidia_cudnn_cu12-9.10.2.21-py3-none-manylinux_2_27_x86_64.whl
nvidia_cufft_cu12-11.3.3.83-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl
nvidia_cusolver_cu12-11.7.3.90-py3-none-manylinux_2_27_x86_64.whl
nvidia_cusparse_cu12-12.5.8.93-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl
nvidia_cusparselt_cu12-0.7.1-py3-none-manylinux2014_x86_64.whl
nvidia_nccl_cu12-2.27.5-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl
nvidia_nvshmem_cu12-3.3.20-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl
torch-2.9.0a0+git1c57644-cp312-cp312-linux_x86_64.whl
torch-2.9.1-cp312-cp312-manylinux_2_28_x86_64.whl
triton-3.4.0-cp312-cp312-linux_x86_64.whl
triton-3.5.1-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl

Build Info

  • ROCm Version: 7.1
  • Python Version: 3.12
  • GPU Architectures: gfx942
  • Commit: 035f0f1

Installation

These wheels are automatically referenced by the PyPI index at:
https://EmbeddedLLM.github.io/vllm-rocm/simple/

Use: pip install vllm-rocm --index-url https://EmbeddedLLM.github.io/vllm-rocm/simple/

Loading

ROCm Wheels - 2025-11-18

18 Nov 05:49
@github-actions github-actions
wheels-20251118-054933
15899db

Choose a tag to compare

View all tags
ROCm Wheels - 2025-11-18

Large ML framework wheels for vLLM ROCm

Included Wheels

torch-2.9.0a0+git1c57644-cp312-cp312-linux_x86_64.whl
triton-3.4.0-cp312-cp312-linux_x86_64.whl

Build Info

  • ROCm Version: 7.1
  • Python Version: 3.12
  • GPU Architectures: gfx942
  • Commit: 15899db

Installation

These wheels are automatically referenced by the PyPI index at:
https://EmbeddedLLM.github.io/vllm-rocm/simple/

Use: pip install vllm-rocm --index-url https://EmbeddedLLM.github.io/vllm-rocm/simple/

Loading

ROCm Wheels - 2025-11-17

17 Nov 14:00
@github-actions github-actions
wheels-20251117-140012
3735664

Choose a tag to compare

View all tags
ROCm Wheels - 2025-11-17

Large ML framework wheels for vLLM ROCm

Included Wheels

torch-2.9.0a0+git1c57644-cp312-cp312-linux_x86_64.whl
triton-3.4.0-cp312-cp312-linux_x86_64.whl

Build Info

  • ROCm Version: 7.1
  • Python Version: 3.12
  • GPU Architectures: gfx942
  • Commit: 3735664

Installation

These wheels are automatically referenced by the PyPI index at:
https://EmbeddedLLM.github.io/vllm-rocm/simple/

Use: pip install vllm-rocm --index-url https://EmbeddedLLM.github.io/vllm-rocm/simple/

Loading

ROCm Wheels - 2025-11-17

17 Nov 11:47
@github-actions github-actions
wheels-20251117-114734
508c45a

Choose a tag to compare

View all tags
ROCm Wheels - 2025-11-17

Large ML framework wheels for vLLM ROCm

Included Wheels

torch-2.9.0a0+git1c57644-cp312-cp312-linux_x86_64.whl
triton-3.4.0-cp312-cp312-linux_x86_64.whl

Build Info

  • ROCm Version: 7.1
  • Python Version: 3.12
  • GPU Architectures: gfx942
  • Commit: 508c45a

Installation

These wheels are automatically referenced by the PyPI index at:
https://EmbeddedLLM.github.io/vllm-rocm/simple/

Use: pip install vllm-rocm --index-url https://EmbeddedLLM.github.io/vllm-rocm/simple/

Loading