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]: when dtype='bfloat16', batch_size will cause different inference results
- [Feature]: MLA Support
- [Bug]: Unable to use vLLM for serving fine tuned mistral model
- [Usage]: Get time statistics with each request
- [Kernel] sliding window support in paged_attention_v1/v2 kernels
- [Bug]: No CUDA GPUs are available on 'CPU' use
- [Misc]: a question about chunked-prefill in flash-attn backends
- [Usage]: Profiling Prefill and Decode Phases Separately
- [Bug]: run vllm api with docker
- [Bug]:vllm-0.4.2 running error
- Docs
- Python not yet supported