Pinned Loading

1. vllm-project/vllm vllm-project/vllm Public

   A high-throughput and memory-efficient inference and serving engine for LLMs

   Python 82.9k 18.1k

2. vllm-project/vllm-omni vllm-project/vllm-omni Public

   A framework for efficient model inference with omni-modality models

   Python 5.1k 1.1k

3. kvcache-ai/Mooncake kvcache-ai/Mooncake Public

   Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

   C++ 5.6k 850

4. dragonflydb/dragonfly dragonflydb/dragonfly Public

   A modern replacement for Redis and Memcached

   C++ 30.7k 1.2k

5. Kedis Kedis Public

   🚀 A persistent RESP-compatible KV store in C, architected with io_uring, eBPF, and RDMA to integrate pluggable multi-engine storage with kernel-bypass data plane optimizations.

   C 1

6. RL-Align/RL-Kernel RL-Align/RL-Kernel Public

   Modern RL Post-training Infrastructure: Optimized for NVIDIA/AMD GPUs with a focus on vLLM and DeepSpeed integration, CUDA/ROCm/Triton kernels, and transparent hardware-aware scaling.

   Python 124 21