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
- [Bugfix][MooncakeStore] Zero the unwritten tail pages of async-loaded blocks
- [Bug]: GLM-5.3 KDA keeps stale merged convolution weights after refit
- [ROCm][Perf] Pad fp16/bf16 GEMM weight row stride for L2 cache
- [Bugfix] Support Mamba2 TP group replication
- [Bugfix][KV Cache] Emit BlockRemoved only after the last physical copy is evicted
- [CI][ROCm] Make image dependencies cache-safe
- feat: add Qwen 3.8 and Qwen 3.8 MoE model architectures and configs
- [ROCm] Route AWQ linear through choose_mp_linear_kernel
- Fix moe scratch buffer sizing for the TP>1 and DP>1 case
- [Bugfix] Fix DeepSeek V4 K-cache gather for strided block tables
- Docs
- Python not yet supported