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 supported29 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Core] Enable KimiLinear (KDA/GDN + MLA) PD Separation via NIXL
- [Bugfix][Model] GraniteMoE: load FP8_DYNAMIC expert weight_scale tensors
- [Bug]: Negative CUDA graph memory estimation (-35 GiB) with MTP speculative decoding leads to severe KV cache over-allocation and OOM
- [Bugfix] Harden allowed_token_ids metadata for spec-decode
- [Security] Fix remote DoS from grammar-rejected spec tokens padded with -1
- Revert "[Bugfix][MoE] Snapshot max_cudagraph_capture_size into FusedMoEConfig" (#44613)
- [Rust Frontend][RFC] Request tracing for the Rust frontend
- Add weights padding for fp8 per-block online quantization
- [Feature]: [Metrics] Add per-request preemption count to Prometheus histogram
- [Feature]: Explicit cache breakpoints and cache usage accounting in OpenAI-compatible API
- Docs
- Python not yet supported