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 supported61 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Recipe] Add DeepSeek V4.1 Flash Ascend A3 W8A8 configuration
- [ROCm][Perf] Add Triton skinny GEMM for 6-128 rows on RDNA4
- [Bugfix] Fix KV cache pages for hybrid models with draft layers
- [XPU][LoRA] Support unquantized MoE LoRA
- [RFC] Expose allocator-issued KV block generations to asynchronous connectors
- [Bug]: DeepSeek-V4.1: wrong output when the last chunk of a chunked prefill runs as a piecewise CUDA graph
- [Tokenizer] Reject reserved special tokens in DeepSeek V4.1 requests
- [Feature]: Qwen4Exp PLE cpu_offload without UVA (NVIDIA Confidential Computing)
- [Perf][DSv4.1] Replay one row for prefill chunks far from the prompt end
- [Feature][Multimodal] Make the media fetch User-Agent configurable
- Docs
- Python not yet supported