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 supported23 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Performance]: RTX 6000 PRO - FP8 in sglang is faster
- [RFC]: Enable libtorch-ABI-stable vLLM cuda wheels
- [Bug]: Is Flashinfer Attn backend supposed to work with FP8 KV cache on Hopper?
- [Bugfix][Core] Load plugins in new processes created by `fork`
- [Log] allow customize fileinfo to import pkg file
- Granite4 Quantization Bug Fix
- [Bugfix] fix CUDA illegal memory access when sleep mode is triggered during request processing
- [Bug]: Multinode inference request with Ray and vLLM crashes - regression from vLLM v0.7.3
- [Bug]: Value error, Tensor parallel size (2) cannot be larger than the number of available GPUs (1).
- [Bugfix] Temporarily disable group quant rms norm fusion
- Docs
- Python not yet supported