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 supported59 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Rust Frontend] Multimodal and LoRA in the engine-free renderer
- [Rust Frontend][gRPC] Add the Render service with RenderChat
- [ROCm][Perf][MoE] Run the router GEMM before the shared-expert fork
- [Bugfix][NIXL] Decline remote prefill reads after the producer's KV lease expired
- [Feature]: Tighter integration with Compressed-Tensors by consolidating and converting targets to vLLM
- [XPU][CI]Migrate Distributed Torchrun + Shutdown to intel_gpu_k8s
- [Bugfix][Model Loader] Stop the EP weight filter from skipping a draft model's experts
- [Rust Frontend] Add the Poolside tool parser
- [Refactor][Multimodal] Share grid_thw encoder CUDA graph code via a mixin
- [Quantization][Kernel] Unify MXFP6 linear activation scheme gate and propagate per-layer target overrides
- Docs
- Python not yet supported