Pinned Loading

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

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

   Python 85.2k 18.9k

2. vllm-project/llm-compressor vllm-project/llm-compressor Public

   Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM

   Python 3.5k 562

3. On-Device-Agent-for-adaptive-display-optimization On-Device-Agent-for-adaptive-display-optimization Public

   We present a novel on-device hybrid agent combining LLMs with retrieval-augmented generation for real-time display optimization. The system achieves 92% accuracy with CoreML acceleration delivering…

   Swift 1

4. ARS-Adaptive-Reasoning-Suppression-for-Efficient-Large-Reasoning-Language-Models ARS-Adaptive-Reasoning-Suppression-for-Efficient-Large-Reasoning-Language-Models Public

   Adaptive Reasoning Suppression for Efficient Large Reasoning Language Models

5. distributed-inference-engine-nano-vLLM distributed-inference-engine-nano-vLLM Public

   Python

6. distributed-training-infra-demo-megatron distributed-training-infra-demo-megatron Public

   Python