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
- [Spec Decode] Fix skipped drafter draft token clearing
- [Performance]: Hybrid + KV offloading discards reusable divergent prefix hits — offloaded boundary state is never consulted
- [Bugfix][MoE] Fall back from monolithic NVFP4 for simulated routing
- [Profiling] Add NVTX/torch-profiler annotations to V2 model runner and DFlash speculator
- [Bug]: GPT-OSS reasoning retains matched stop string when include_stop_str_in_output=false
- [Doc]: vLLM's default NIXL connector is ~100× slower than the push connector on non-RDMA hardware, and the fix is undocumented
- [Bug]: lm-format-enforcer 0.11.3 integration is incompatible with vLLM 0.26.0 due to stale MistralTokenizer import path
- [Bugfix] Encode special tokens found in text for MistralCommonBackend in multimodal processors
- fix(mooncake): Restore TP replication awareness for DCP and reduce write amplification
- [MooncakeStore] Report KV load tier in cache events
- Docs
- Python not yet supported