Lian

LLM inference engineer in training · vLLM internals · KV cache · prefix caching · CUDA/Triton (learning)

代表作品 / 项目

qwen3-prefix-cache-bench⭐ 0Reproducible Qwen3-1.7B prefix cache benchmark on RTX 3070 Laptop (8GB). Hand-written reference inference loop + vLLM v1 comparison.
derLogik⭐ 0Profile README
tiny-qwen⭐ 0A minimal PyTorch re-implementation of Qwen 3.5
vllm⭐ 0A high-throughput and memory-efficient inference and serving engine for LLMs
multi-model-agent⭐ 0Multi-agent collaboration system using LangGraph + FastAPI + Next.js (engineering demo, not inference work).

条目信息来自其公开主页与公开发布内容。按本站规范，页面不展示任何联系方式。需要更正或删除？通过收录与更正通道提交，24 小时内处理。