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 supported13 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Feature]: Add prefix cache state metrics for KV cache monitoring
- [Bug]: LoRA MoE Eager Mode Changes Outputs
- [Feature][Speculative Decoding]: Multi Modal Draft Model Support
- Scheduler: skip KV-blocked requests to prevent blocking (#31731)
- [config] fix error occurs when loading local mode(starting with /)
- [9/n] Migrate CUTLASS FP4, sparse, and W4A8 kernels to libtorch stable ABI
- [14/n] Migrate _moe_C to torch stable ABI
- Make Longcat-Flash N-gram inputs compile-friendly and fix zero-expert MoE routing#33528
- [Bugfix] Fix Gemma3 multimodal placeholder replacement
- Introduce PaddingConfig to combine GPU cudagraph_capture_sizes and TPU num_tokens_paddings
- Docs
- Python not yet supported