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 supported51 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: Missing `has_cutedsl()` guard in `DeepseekCompressor` (head_dim == 512 path)
- [Frontend] Map unsupported reasoning_effort to nearest supported level
- [Bugfix][Model] Guard DeepSeek V4 compressor CuTe DSL dispatch
- [Model] Enable LoRA support for tower and connector in Llama Nemotron VL
- [Bugfix][Compile] Warn when compile_ranges_endpoints exceed max_num_batched_tokens (#52471)
- [Kernel][AMD] Add MI300X FP8 tuned configs for Qwen3.8-27B-FP8
- [Bugfix][Core] Pin static FP8 quant pattern to group_shape=None
- [LoRA] Support per-request dynamic LoRA scale
- [Bugfix] Surface TorchCodec video decode failures as client errors
- [Bug]: deepseek-v4-flash-0731: Pipeline parallelism is not supported for this model.
- Docs
- Python not yet supported