Factual package intelligence from PyPI

vllm-npu 0.4.2.post2 package intelligence

A high-throughput and memory-efficient inference and serving engine for LLMs

pip install vllm-npu

Current version
0.4.2.post2
Python requirement
>=3.8
License
Apache 2.0
Distribution type
Pure Python wheel
Release files
2 (1 wheels, 1 source)
Download size
1016.3 KiB
Release history
3 releases with files
Median release cadence
0 days

vllm-npu dependencies

PyPI declares 24 unique dependency rules for this release. Environment markers are shown when supplied by the project.

  1. cmake >=3.21
  2. ninja
  3. psutil
  4. sentencepiece
  5. numpy ==1.26.4
  6. requests
  7. py-cpuinfo
  8. transformers >=4.40.0
  9. tokenizers >=0.19.1
  10. fastapi
  11. openai
  12. uvicorn
  13. pydantic >=2.0
  14. prometheus_client >=0.18.0
  15. prometheus-fastapi-instrumentator >=7.0.0
  16. tiktoken ==0.6.0
  17. lm-format-enforcer ==0.10.1
  18. typing_extensions

The compact report shows 18 of 24 declarations. The interactive dependency graph loads the complete metadata.

Compatibility and release files

vllm-npu publishes 1 wheel and 1 source archive for version 0.4.2.post2. Wheel platform tags: any.

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

Release activity and sources

PyPI lists 3 releases with files. The first dated release is ; 3 releases fall within the 365 days preceding the latest dated release. The current release files were uploaded on . The preceding dated release was .