-
Meet LLMc: Beating All Compression with LLMs
We present LLMc, an open-source tool to compress natural language using LLMs as the world's most reference-packed dictionary.
-
Making PyTorch Static: A Step-by-Step Walkthrough
A quick guide to building PyTorch with static linking, with tips to avoid common issues.
-
How to use CUPTI APIs to build a CUDA profiler?
Experiences and lessons learned from building a CUPTI-based CUDA profiler
-
服务器环境配置 Cheat Sheet
Cheat sheet for setting up a server environment
-
llm.c 源码阅读
Reading the source code of llm.c