Archives
- 03 Nov PDL 详解:让相邻 GPU kernel 首尾重叠——原理、写法、各框架实践与踩坑总结
- 02 Nov LLM 推理框架的 Autotune 设计指南:各家最佳实践与可落地的设计要点
- 18 Aug 廉价生成之后:AI Agent 与再生式软件工程
- 23 Jul Removing the Legacy TensorRT Backend from TensorRT-LLM: A Retrospective
- 06 Jul Piecewise CUDA Graph and Breakable CUDA Graph for LLM Inference
- 23 Jun When NVLS Is "Supported" on H100, Why Does AllReduce Take Another Path?
- 01 Jun GDPval Bench introduction
- 20 Apr Patch 1: Useful skills exploration for LLM infra frameworks
- 03 Apr Deep Dive: AllReduce and AllReduce Fusion in TensorRT-LLM
- 16 Mar Optimizing Nemotron v3 Super in TensorRT-LLM
- 11 Mar TerminalBench introduction
- 10 Mar How to setup my blog?
- 10 Mar IFBench introduction