Posts
What Is Model Quantization
· β˜• 5 min read
1. What Is Model Quantization Model quantization is the process of converting the weights and activations of a high-precision model (usually 32-bit floating point FP32 or 16-bit floating point FP16) into a low-precision model (such as 8-bit integer INT8). The value range of FP32 is -3.4*10^38 to 3.4*10^38, with 4 billion values.

Kubernetes Base Environment Requirements
· β˜• 4 min read
1. Base Packages Kubernetes version β‰₯ 1.18 socat Required conntrack Required ebtables Optional, but recommended ipset Optional, but recommended ipvsadm Optional, but recommended 1 apt-get -y install socat conntrack ebtables ipset ipvsadm 2. Port Requirements 2.1 Base Node Services Service Protocol Action Start Port End Port Comment ssh TCP allow 22 22 Node remote management docker TCP allow 2375 2376 Docker remote communication etcd TCP allow 2379 2380 etcd cluster communication 2.

How to Upgrade the cgroup Version of a Kubernetes Node
· β˜• 3 min read
1. Interface Path Differences Between cgroup v1 and v2 v1 1 2 3 4 /sys/fs/cgroup/cpu/cpu.cfs_quota_us /sys/fs/cgroup/cpu/cpuacct.usage /sys/fs/cgroup/memory/memory.limit_in_bytes /sys/fs/cgroup/memory/memory.usage_in_bytes v2 1 2 3 4 /sys/fs/cgroup/cpu.max /sys/fs/cgroup/cpu.stat /sys/fs/cgroup/memory.max /sys/fs/cgroup/memory.current cgroup v2 is the upgraded version of v1, with advantages such as more unified resource hierarchy management and precise resource isolation. But it also means that when writing code, the paths for reading the relevant interface files are different, so compatibility handling is required.

Using claude-code on a Server
· β˜• 3 min read
The same applies to a desktop environment. 1. Prepare the node.js environment Install nvm 1 curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.40.3/install.sh | bash 1 2 echo 'export NVM_DIR="$([ -z "${XDG_CONFIG_HOME-}" ] && printf %s "${HOME}/.nvm" || printf %s "${XDG_CONFIG_HOME}/nvm")"' >> ~/.bashrc echo '[ -s "$NVM_DIR/nvm.sh" ] && \. "$NVM_DIR/nvm.sh"' >> ~/.bashrc 1 source

Common NPU Operations and Fault Handling
· β˜• 1 min read
Content referenced or recorded while troubleshooting, continuously updated 1. Mounting Devices into a Container 1 export IMAGE=ascendai/pytorch:2.1.0 1 2 3 4 5 6 7 8 9 10 nerdctl run --security-opt apparmor=unconfined --security-opt seccomp=unconfined --rm -it --ipc=host \ --device=/dev/davinci7 \ --device=/dev/davinci_manager \ --device=/dev/devmm_svm \ --device=/dev/hisi_hdc \ -v /usr/local/Ascend/driver:/usr/local/Ascend/driver \ -v /usr/local/Ascend/add-ons/:/usr/local/Ascend/add-ons/ \ -v /usr/local/sbin/npu-smi:/usr/local/sbin/npu-smi \ ${IMAGE} \ /bin/bash 2.