vLLM
High-throughput, memory-efficient inference and serving engine for LLMs
A high-throughput and memory-efficient inference and serving engine for LLMs
Last updated: 2026-10-11T07:10:00.949983+00:00
Evidence Chain
| Field | Value | Source | Tier | Fetched | Confidence |
|---|---|---|---|---|---|
| archived | No | https://api.github.com/repos/vllm-project/vllm | 1 | 2026-10-11T07:10:00.949983+00:00 | 0.99 |
| description | A high-throughput and memory-efficient inference and serving engine for LLMs | https://api.github.com/repos/vllm-project/vllm | 1 | 2026-10-11T07:10:00.949983+00:00 | 0.99 |
| license | Apache-2.0 | https://api.github.com/repos/vllm-project/vllm | 1 | 2026-10-11T07:10:00.949983+00:00 | 0.99 |
| open_issues | 8673 | https://api.github.com/repos/vllm-project/vllm | 1 | 2026-10-11T07:10:00.949983+00:00 | 0.99 |
| page_title | GitHub - vllm-project/vllm: A high-throughput and memory-efficient inference and serving engine for LLMs | https://github.com/vllm-project/vllm | 2 | 2026-10-11T07:10:00.949983+00:00 | 0.9 |
| pushed_at | 2026-10-11T07:10:05Z | https://api.github.com/repos/vllm-project/vllm | 1 | 2026-10-11T07:10:00.949983+00:00 | 0.99 |
| stars | 93541 | https://api.github.com/repos/vllm-project/vllm | 1 | 2026-10-11T07:10:00.949983+00:00 | 0.99 |
| topics | amd, blackwell, cuda, deepseek, deepseek-v3, gpt, gpt-oss, inference, kimi, llama, llm, llm-serving, model-serving, moe, openai, pytorch, qwen, qwen3, tpu, transformer | https://api.github.com/repos/vllm-project/vllm | 1 | 2026-10-11T07:10:00.949983+00:00 | 0.99 |