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 supported31 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [V1][LoRA] Version prefix-cache keys for local runtime LoRA reloads
- [Bug]: Repeated `start_profile`/`stop_profile` in the same process produces no trace files
- fix(profiler): rebuild one-shot torch profiler each round so repeated start/stop writes traces
- Pass quant config to Qwen3Next embeddings
- [RFC]: Kernel-agnostic constant-stride (layer-major) KV cache layout for KV connectors
- feat: MLA prefill per-group FP8 fused output
- [MM][CG] Support ViT full CUDA graph for DeepSeek-VL2
- [P/D][Mooncake] Send KV to D when prefill first token is a stop token
- fix(transformers_utils): parse compact sentence-transformers pooling_mode (>=5.4.0)
- [Core] Drop stale scheduler requests before scheduling
- Docs
- Python not yet supported