Factual package intelligence from PyPI

vllm-rocm 0.6.3 package intelligence

A high-throughput and memory-efficient inference and serving engine for LLMs with AMD GPU support

pip install vllm-rocm

Current version
0.6.3
Python requirement
>=3.8
License
Apache 2.0
Distribution type
Includes compiled wheel
Release files
1 (1 wheels, 0 source)
Download size
35.7 MiB
Release history
1 releases with files
Median release cadence
Not enough dated releases

vllm-rocm dependencies

PyPI declares 43 unique dependency rules for this release. Environment markers are shown when supplied by the project.

  1. psutil
  2. sentencepiece
  3. numpy <2.0.0
  4. requests >=2.26.0
  5. tqdm
  6. py-cpuinfo
  7. transformers >=4.45.0
  8. tokenizers >=0.19.1
  9. protobuf
  10. aiohttp
  11. openai >=1.40.0
  12. uvicorn
  13. pydantic >=2.9
  14. pillow
  15. prometheus-client >=0.18.0
  16. prometheus-fastapi-instrumentator >=7.0.0
  17. tiktoken >=0.6.0
  18. lm-format-enforcer ==0.10.6

The compact report shows 18 of 43 declarations. The interactive dependency graph loads the complete metadata.

Compatibility and release files

vllm-rocm publishes 1 wheel and 0 source archives for version 0.6.3. Wheel platform tags: manylinux_2_34_x86_64.manylinux_2_35_x86_64.

Declared Python classifiers: 3.10, 3.11, 3.12, 3.8, 3.9.

Release activity and sources

PyPI lists 1 release with files. The first dated release is ; 1 release falls within the 365 days preceding the latest dated release. The current release files were uploaded on .