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
- [Performance][MLA] Use FP16 logits for sparse indexer
- [Bug]: OpenAI `strict` flag on tool definitions is rendered into the model-visible chat template, changing tool-call behaviour
- [CPU] [1/n] Start migrating the CPU extension to the libtorch stable ABI
- [Bugfix][Parser] Recover DeepSeek V4 tool calls with malformed DSML wrappers
- [Feat][Bench] Allow random dataset to sample real tokens from --dataset-path
- [Bugfix] Invalidate LazyDict cache on __setitem__
- [Spec Decode] Warn that speculative max_model_len has no effect
- [Bug]: Qwen3.6-27B (dense Gated-DeltaNet) permanently hard-wedges the V1 engine — two reproducible modes (2 large images; long multi-turn text), possibly related
- [Perf] Add opt-in custom all-reduce max-size override
- [Bug]: Qwen3.5-9B hybrid-GDN + dynamic LoRA on H20 produces NaN output ("!" tokens) for long sequences — punica Triton kernel bug
- Docs
- Python not yet supported