vllm
https://github.com/vllm-project/vllm
Python
A high-throughput and memory-efficient inference and serving engine for LLMs
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported13 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [wip] explore using layerwise reloading utils for fp8 online quant
- [CI Failure]: mi325_1: Multi-Modal Models Test (Standard)
- [CI Failure]: mi325_1: Multi-Modal Models Test (Extended) 1
- Add shutdown timeout CLI and changed shutdown function to send SIGTERM to worker processes before SIGKILL
- Add Kimi-Audio-7B ASR support for /v1/audio/transcriptions
- [Usage]: about the Chinese documents
- [Bug]: [Docker.cpu build] incomplete type ‘qk_vec_type’ {aka ‘void’} used in nested name specifier
- [RFC]: How will vLLM adapt to more diverse KVCacheSpecs?
- [Bug]: When loading LoRA via load_lora_adapter, the inference becomes very slow with high CPU usage
- [Performance][CPU Backend]: 40% Performance drop observed on AWQ models from version 0.12.0 vs version 0.11.2
- Docs
- Python not yet supported