1XGrammar: Efficient, Flexible and Portable Structured Generation for LLM (opens in new tab)(github.com)12ruihangl1y ago1
2High-Throughput Low-Latency LLM Serving with MLCEngine (opens in new tab)(blog.mlc.ai)8ruihangl1y ago0
3Universal LLM Deployment Engine with ML Compilation (opens in new tab)(blog.mlc.ai)17ruihangl1y ago7
4Run Llama2-70B in Web Browser with WebGPU Acceleration (opens in new tab)(webllm.mlc.ai)9ruihangl2y ago6