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]: Fails to initialize LLM engine on neuron with error - NeuronWorker.__init__() missing 1 required positional argument: 'cache_config'
- [Usage]: Cannot load model on 2 4090
- [Feature]: Support for JetMoE model
- [Usage]: long prompt logits calculation
- [Bug]: Longchat-7b-v1.5-32k get different result with TP4 and TP2
- [Bug]: Concurrent requests are non-deterministic
- vLLM added to self-created architectures
- [Frontend] Entrypoint for hosting local Kobold Lite chat interface
- [Bug]: failed to run vllm on two nodes
- [Bug]: ValueError: Can't set signal handler for SIGINT while SIGINT is being deferred within a DeferSigint context when tp>1
- Docs
- Python not yet supported