1. What the Image Tag Suffixes Mean base/cuda: includes the CUDA runtime runtime: builds on base, adding the CUDA math libraries and the NCCL and cuDNN runtimes devel: builds on runtime, adding headers and the development tools used to build CUDA images; particularly useful for multi-stage builds cuddn: builds on the above, adding the cuDNN neural network acceleration library

1. Compiling Models with TensorRT-LLM 1.1 Introduction to TensorRT-LLM When using TensorRT, you usually need to convert the model to ONNX format, then convert the ONNX to TensorRT format, and finally run inference in TensorRT or Triton Server. But this conversion process is not simple, and you often run into

1. Memory Alignment Arrange the fields inside a struct from largest to smallest. This reduces memory footprint. Install the fieldalignment tool 1 go install golang.org/x/tools/go/analysis/passes/fieldalignment/cmd/fieldalignment@latest Analyze and fix memory alignment 1 2 3 4 5 6 7 8 9 fieldalignment -fix ./... /Users/shaowenchen/Code/app/config/config.go:136:14: struct with 32 pointer bytes could be 24 /Users/shaowenchen/Code/app/config/config.

Unlike on CentOS or Ubuntu, where we feel that mv is faster than cp, when you build an image with a Dockerfile, using Run cp is faster than Run mv. This post presents the test and verification data behind that. 1. Test Setup Machine environment Ubuntu 20.04.1 LTS 32C

1. The container’s ulimit is set too low Error message: 1 2 3 4 5 6 7 CheckpointDir: /root/.obsutil_checkpoint OutputDir: /root/.obsutil_output runtime: mlock of signal stack failed: 12 runtime: increase the mlock limit (ulimit -l) or runtime: update your kernel to 5.3.15+, 5.4.2+, or 5.5+ fatal error: mlock failed Under Docker, you can add the ulimit parameter at startup 1 docker run -it --ulimit memlock=-1 .