GitHub / vllm-project / vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
JSON API: http://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vllm-project%2Fvllm
PURL: pkg:github/vllm-project/vllm
Stars: 53,441
Forks: 8,990
Open issues: 2,687
License: apache-2.0
Language: Python
Size: 64.9 MB
Dependencies parsed at: Pending
Created at: over 2 years ago
Updated at: 2 days ago
Pushed at: 2 days ago
Last synced at: 2 days ago
Commit Stats
Commits: 4106
Authors: 701
Mean commits per author: 5.86
Development Distribution Score: 0.882
More commit stats: https://commits.ecosyste.ms/hosts/GitHub/repositories/vllm-project/vllm
Topics: amd, cuda, deepseek, gpt, hpu, inference, inferentia, llama, llm, llm-serving, llmops, mlops, model-serving, pytorch, qwen, rocm, tpu, trainium, transformer, xpu
Funding Links https://github.com/sponsors/vllm-project, https://opencollective.com/vllm