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 supported36 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [PD][NixlPush][Bugfix] Fix prefix caching
- Add tiering offloading metrics
- [Spec Decode][V1] Warm Eagle and DFlash/DSpark spec-decode Triton kernels at startup
- [ROCm][CI] Loosen block-FP8 fused MoE test tolerance for large-K shapes
- [Bugfix][LoRA] Add embedding_modules for Qwen3.5 CausalLM
- [Bug]: [MRV2] MTP speculative decoding crashes with cudaErrorStreamCaptureUnsupported during CUDA graph capture
- [Do Not Merge][2/N][Attention] Enable masked MHA for sparse MLA prefills
- Fixes Issue #48749, Co-authered by Google Antigravity
- [Kernel] ReplaySSM: cache SSM inputs for faster Gated DeltaNet standard decode
- [Bugfix][Multimodal] Fix M-RoPE media mapping for chunked prefill and multi-media chunks
- Docs
- Python not yet supported