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 supported4 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: Nccl Test Error
- [V1] E2E (prompt )logprobs tests (PR 3/N for v1 sample and prompt logprobs support)
- [Usage]: How to reach 100% GPU Compute Utilization ?
- [Bug]: failure when compiling httptools
- [Feature]: 【support tts llm like cosyvoice2.0】
- [Doc]: Invalid JSON examples in Engine Args Document
- [New Model]: Cosmos-1.0-Autoregressive (World Foundation Models)
- [V1] Move more control of kv cache initialization from model_executor to EngineCore
- [Spec Decode] feat: support LoRA with speculative decoding
- [Misc] Support register quantization method out-of-tree
- Docs
- Python not yet supported