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 supported62 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Core][NIXL] Transfer KV between different P/D KV cache group plans
- [Bug]: GLM-5.3-Flash NVFP4 on B300: CUDA illegal access persists with MTP disabled; blocking/eager reports persistent_topk
- [Bugfix][Attention] Demote CG support to UNIFORM_BATCH with varlen bound for MLA and KDA
- [Frontend][Metrics] Count requests cancelled by client disconnect
- [Feature]: Reload speculative draft model weights from a new checkpoint at runtime (online speculator updates)
- [Spec Decode] Add reload_draft_weights to hot-swap an updated draft model
- [Metrics] Count client-aborted requests in vllm:request_success
- [Bug]: Sparse weight patches fail on tied embeddings when lm_head and embed_tokens land in different chunks
- [ROCm][DSv4.1][Perf] Route gfx942 mHC seams through aiter mhc_fused_post_pre_delayed
- [Attention] FA4 hd512 GQA on Blackwell for DiffusionGemma
- Docs
- Python not yet supported