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
- [Performance] [Speculative decoding]: Compute prepare inputs of the scoring model on GPU
- why our performance so low when compare with sglang(https://github.com/sgl-project/sglang?tab=readme-ov-file#benchmark-and-performance)
- [Usage]: Streaming response
- [Bug]: Mixtral 8-way TP with --enable-lora crashes with CUDA illegal memory access error
- [Bug]: cuda OOM errors persist across requests.
- [Bug]: Unable to build image from `vllm` repo Dockerfile
- [Bug]: error: Segmentation fault(SIGSEGV received at time)
- [Misc]: Why doesn't a larger block size result in faster performance?
- [Usage]: Only one thread is utilising when vllm is use with the llamaindex framework on the cpu.
- [Bug]: First input (bf16) and second input (uint8) must have the same dtype!
- Docs
- Python not yet supported