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]: speculative decoding under pipeline parallelism produces wrong output with --no-async-scheduling
- [Bugfix][Spec Decode] Preserve constant effective K schedule semantics
- [Security] Fix ReDoS in validation error path sanitizer
- [Bug]: VLLM 0.27.0 has not been fixed MiniCPM-V-4.6 startup fails (because vLLM expects k_proj in a fused-qkv ViT attention layer)
- [Frontend] Honour --host for the run-batch Prometheus metrics server
- [Perf] Skip the per-step q concat in TRITON_MLA decode by passing q_nope/q_pe through separate kernel pointers
- [Feature][DSpark]: Enable varlen for Kimi K3 (KDA)
- [Feature][DSpark]: Enable varlen for Nemotron-H (Mamba)
- [Feature][DSpark]: Enable varlen for Qwen 3.x (GDN)
- [Feature][DSpark]: Polish DSpark adaptive timings
- Docs
- Python not yet supported