| Documentation | Blog | Paper | Twitter/X | User Forum | Developer Slack |
Caution
The ROCm/vllm repository is retired, please use the upstream repository
A high-throughput and memory-efficient inference and serving engine for LLMs
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
| Documentation | Blog | Paper | Twitter/X | User Forum | Developer Slack |
Caution
The ROCm/vllm repository is retired, please use the upstream repository
A high-throughput and memory-efficient inference and serving engine for LLMs