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 supported3 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: Error loading bitsandbytes 4bit model when the quant_storage is torch.bfloat16
- [Interleaved ATTN] Support for Mistral-8B
- fix json serialization issue
- [Core] Update to outlines > 0.1.4
- [WIP] V1 LoRA support
- [Kernel] Remove hard-dependencies of Speculative decode to CUDA workers
- [Bug] Streaming output error of tool calling has still not been resolved.
- [Bug]: Speculative Decoding without enabling eager mode returns gibberish output after some tokens.
- [Doc]: Docker+vllm+fastchat deploys multimodal large model Qwen2-vl-7b-instruct(docker+vllm+fastchat部署多模态大模型Qwen2-vl-7b-instruct)
- [Installation]: Segmentation fault when building Docker container on WSL
- Docs
- Python not yet supported