Popular repositories Loading

1. my-nano-vllm my-nano-vllm Public

   A compact inference-systems project derived from nano-vLLM, focused on measurable GPU-kernel and scheduling experiments.

   Python

2. Adaptive-SpecDecode-Lab Adaptive-SpecDecode-Lab Public

   Python

3. opencode-acp opencode-acp Public

   Forked from ranxianglei/opencode-acp

   稳定可用Active Context Pruning — model-driven context management for OpenCode ，200K tokens is enough. ，主动压缩上下文，20w token足以

   TypeScript

4. acp-kernel acp-kernel Public

   Forked from ranxianglei/acp-kernel

   压缩内核ACP compression & state management engine — standalone, zero runtime dependencies

   TypeScript

5. vllm vllm Public

   Forked from vllm-project/vllm

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

   Python

6. llm-d-inference-sim llm-d-inference-sim Public

   Forked from llm-d/llm-d-inference-sim

   A lightweight, configurable, and real-time simulator designed to mimic the behavior of vLLM without the need for GPUs or running actual heavy models.

   Go