No known security advisories.
The current version has no OSV.dev malware reports and no critical or high-severity vulnerabilities.
vllm has 5.8M monthly downloads and 86K GitHub stars. Version 0.24.0 supports Python <3.15,>=3.10, first published in 2023.
It is actively maintained under a permissive license, last released in Jun 2026.
It is built on top of aiohttp, anthropic and apache-tvm-ffi. It is used by 187 tracked packages, including rank-llm, vllm-rbln and cjm-transcription-plugin-voxtral-vllm.
GitHub topics include gpt, llm and pytorch.
Package Insights
Score breakdown - each component scores 0-100, weighted by percentage
Maintenance
100
Popularity
99
Adoption
60
Community
90
Provenance
0
How the maintenance status was determined
Last commit
0 days ago
Monthly downloads
5,807,156
•
Active
Activity within 30 days
Stable
Activity within 31-180 days
Minimal
Activity within 181-365 days, or no activity data
At Risk
No activity for > 365 days, but > 10,000 monthly downloads
Archived
Repository flagged as archived on GitHub
How the popularity category was determined
Monthly downloads
5,807,156
Stars
85,667
Stars per 1k downloads
14.75
Industry Standard
> 10,000,000 monthly downloads
Hidden Gem
< 0.5 stars per 1k downloads and > 100,000 monthly downloads
•
Community Favorite
> 5 stars per 1k downloads
Rising Star
Balanced ratio of stars to downloads
Unknown
Fewer than 1,000 monthly downloads, or no star data
How download momentum is calculated
Week daily avg
166,657
Month daily avg
193,572
Momentum
-13.9%
((week_daily_avg - month_daily_avg) / month_daily_avg) * 100Python version support tiers
requires_python
<3.15,>=3.10
Cutting Edge
Minimum supported version is 3.12 or newer
•
Modern
Minimum supported version is 3.9, 3.10, or 3.11
Legacy
Supports 3.8 or older (or Python 2)
Unknown
No requires_python specified or unparseable
License categories
License
Apache-2.0
•
Permissive
MIT, Apache, BSD, ISC, Unlicense, CC0, etc.
Copyleft
GPL, LGPL, AGPL, MPL, EPL, etc.
Proprietary
Commercial, all rights reserved, custom EULAs
Unknown
No license specified, or none of the above match
How the release cadence was determined
Last release
8 days ago
Total releases
90
Releases/year
29.5
•
Rapid
Last release within 365 days and > 12 releases/year
Regular
Last release within 365 days
Slow
Last release 366-730 days ago
Stalled
Last release > 730 days ago, or no releases
Unknown
No usable release date available
How contributor risk was determined
Contributors
2,891
Monthly downloads
5,807,156
High Load
≤ 2 contributors and ≥ 50,000 monthly downloads
Moderate Load
< 10 contributors and ≥ 500,000 monthly downloads
Low Load
< 25 contributors and ≥ 5,000,000 monthly downloads, or sole maintainer with ≥ 10,000 monthly downloads
•
Balanced
Enough contributors for the package's popularity
Unknown
No contributor data available
Engagement
97
Issue Burden
22.8
per 1k stars
Discussions
5.7
per 1k stars
Fork Ratio
15.1%
contrib / forks
Stale Release
No
PR Velocity
Active
Weekly Downloads
GitHub Stars
Not all downloads include detailed metadata. Breakdowns reflect the subset that does.
Downloads by OS
Linux
92.0K
Windows
6.2K
macOS
4.4K
Python Versions
3.12
53.2%
54.2K
3.11
21.0%
21.4K
3.10
13.0%
13.3K
3.13
8.2%
8.4K
3.14
4.6%
4.7K
Top Countries
1.
US
58.7K
US
2.
KR
8.9K
KR
3.
GB
5.5K
GB
4.
CN
4.2K
CN
5.
SG
3.4K
SG
6.
SE
2.6K
SE
7.
DE
2.3K
DE
8.
IN
2.2K
IN
9.
IS
2.1K
IS
10.
JP
2.0K
JP
Dependencies
72
- aiohttp >=3.13.3
- anthropic >=0.71.0
- apache-tvm-ffi ==0.1.9
- blake3
- cachetools
- cbor2
- cloudpickle
- compressed-tensors ==0.17.0
- depyf ==0.20.0
- diskcache ==5.6.3
- einops
- fastapi <0.137.0,>=0.133.0
- fastsafetensors >=0.3.2
- filelock >=3.16.1
- flashinfer-cubin ==0.6.12
- flashinfer-python ==0.6.12
- humming-kernels ==0.1.6
- ijson
- jsonschema >=4.23.0
- lark ==1.2.2
- llguidance <1.8.0,>=1.7.0
- lm-format-enforcer ==0.11.3
- mcp
- mistral-common >=1.11.3
- model-hosting-container-standards <1.0.0,>=0.1.14
- msgspec
- ninja
- numba ==0.65.0
- numpy
- nvidia-cudnn-frontend >=1.19.1
- nvidia-cutlass-dsl ==4.5.2
- openai >=2.0.0
- openai-harmony >=0.0.3
- opencv-python-headless >=4.13.0
- opentelemetry-api >=1.27.0
- opentelemetry-exporter-otlp >=1.27.0
- opentelemetry-sdk >=1.27.0
- opentelemetry-semantic-conventions-ai >=0.4.1
- outlines-core ==0.2.14
- partial-json-parser
- pillow
- prometheus-client >=0.18.0
- prometheus-fastapi-instrumentator >=8.0.0
- protobuf !=6.30.*,!=6.31.*,!=6.32.*,!=6.33.0.*,!=6.33.1.*,!=6.33.2.*,!=6.33.3.*,!=6.33.4.*,>=5.29.6
- psutil
- py-cpuinfo
- pybase64
- pydantic >=2.12.0
- python-json-logger
- pyyaml
- pyzmq >=25.0.0
- quack-kernels >=0.3.3
- regex
- requests >=2.26.0
- safetensors >=0.6.2
- sentencepiece
- setproctitle
- setuptools <81.0.0,>=77.0.3
- six >=1.16.0
- starlette >=1.0.1
- tiktoken >=0.6.0
- tilelang ==0.1.9
- tokenizers >=0.21.1
- tokenspeed-mla ==0.1.2
- torch ==2.11.0
- torchaudio ==2.11.0
- torchvision ==0.26.0
- tqdm
- transformers >=5.5.3
- typing-extensions >=4.10
- watchfiles
- xgrammar <1.0.0,>=0.2.1
23 optional dependencies
- av[audio]
- datasets[bench]
- fastsafetensors[fastsafetensors]
- helion[helion]
- instanttensor[instanttensor]
- matplotlib[bench]
- mistral-common[audio]
- opentelemetry-api[otel]
- opentelemetry-exporter-otlp[otel]
- opentelemetry-sdk[otel]
- opentelemetry-semantic-conventions-ai[otel]
- pandas[bench]
- plotly[bench]
- runai-model-streamer[runai]
- scipy[audio]
- scipy[bench]
- seaborn[bench]
- smg-grpc-servicer[grpc]
- soundfile[audio]
- soxr[audio]
- tensorizer[tensorizer]
- vllm-gguf-plugin[extra-quant]
- zentorch[zen]
Used By
187
- rank-llm
- vllm-rbln
- cjm-transcription-plugin-voxtral-vllm
- vllm-gguf-plugin
- text2text
- qwerky-vllm-models
- hipporag
- bigcodebench
- sendnn-inference
- factory-sdk
- vllm-spyre
- arbor-ai
- llm-optimized-inference
- kani-ext-vllm
- turboquant-vllm
- orpheus-speech
- llama-index-embeddings-vllm
- londonaicentre-mesa-local
- embedl-models
- cirilla
- vllm-tgis-adapter
- finance-data-llm
- meralion-3-asr
- fasr-asr-qwen3asr
- fasr-asr-qwen3
- llm-engines
- dataflow-421
- happy-vllm
- topicgpt-python
- geoai-vlm
- twinweaver
- text2dataset
- vllm-speculative-autoconfig
- patientsim
- retrieval-heads
- oat-llm
- roboreason
- auralis
- geniusrise-text
- llmlite
- h-adminsim
- sinapsis-vllm
- protollm-api
- async-chat-engine
- himile-model-middleware
- vllm-mock
- finetune-embedder
- papertuner
- easyroutine
- llmq
GitHub Topics
Tags from the package's GitHub repository describing what it does.
Package Information
License
Apache-2.0
First Release
June 19, 2023
Last Release
1 week ago
Last Commit
5 hr ago
Latest Version
0.24.0
Total Releases
90
Contributors
2,891
Open PRs
3,635
Archived
No
Author
vLLM Team
Python Versions
3.10
3.11
3.12
3.13
3.14
Wheels
cp310
cp311
cp38
cp39
Tracking Since
January 6, 2026
Data Updated
July 5, 2026
Data Freshness
Fresh