https://bevisy.github.io/categories/ai/2026-07-27T11:30:00+08:00https://bevisy.github.io/tags/ai/2026-07-27T11:30:00+08:00https://bevisy.github.io/tags/architecture/2026-07-27T11:30:00+08:00https://bevisy.github.io/2026-07-27T11:30:00+08:00https://bevisy.github.io/categories/2026-07-27T11:30:00+08:00https://bevisy.github.io/tags/llm/2026-07-27T11:30:00+08:00https://bevisy.github.io/p/llm-terminology-11-overview-trends/2026-07-27T11:30:00+08:00https://bevisy.github.io/categories/llm%E6%9C%AF%E8%AF%AD%E5%85%A8%E6%99%AF%E5%9B%BE/2026-07-27T11:30:00+08:00https://bevisy.github.io/post/2026-07-27T11:30:00+08:00https://bevisy.github.io/tags/2026-07-27T11:30:00+08:00https://bevisy.github.io/tags/trends/2026-07-27T11:30:00+08:00https://bevisy.github.io/tags/inference-serving/2026-07-27T11:15:00+08:00https://bevisy.github.io/p/llm-terminology-10-inference-serving/2026-07-27T11:15:00+08:00https://bevisy.github.io/tags/sglang/2026-07-27T11:15:00+08:00https://bevisy.github.io/tags/tpot/2026-07-27T11:15:00+08:00https://bevisy.github.io/tags/ttft/2026-07-27T11:15:00+08:00https://bevisy.github.io/tags/vllm/2026-07-27T11:15:00+08:00https://bevisy.github.io/tags/fine-tuning/2026-07-27T11:00:00+08:00https://bevisy.github.io/p/llm-terminology-09-peft-lora/2026-07-27T11:00:00+08:00https://bevisy.github.io/tags/lora/2026-07-27T11:00:00+08:00https://bevisy.github.io/tags/peft/2026-07-27T11:00:00+08:00https://bevisy.github.io/tags/qlora/2026-07-27T11:00:00+08:00https://bevisy.github.io/tags/awq/2026-07-27T10:45:00+08:00https://bevisy.github.io/tags/fp8/2026-07-27T10:45:00+08:00https://bevisy.github.io/tags/gguf/2026-07-27T10:45:00+08:00https://bevisy.github.io/tags/gptq/2026-07-27T10:45:00+08:00https://bevisy.github.io/p/llm-terminology-08-quantization/2026-07-27T10:45:00+08:00https://bevisy.github.io/tags/quantization/2026-07-27T10:45:00+08:00https://bevisy.github.io/tags/gpu/2026-07-27T10:30:00+08:00https://bevisy.github.io/tags/hbm/2026-07-27T10:30:00+08:00https://bevisy.github.io/p/llm-terminology-07-gpu-hardware/2026-07-27T10:30:00+08:00https://bevisy.github.io/tags/nvidia/2026-07-27T10:30:00+08:00https://bevisy.github.io/tags/tensor-core/2026-07-27T10:30:00+08:00https://bevisy.github.io/tags/fsdp/2026-07-27T10:15:00+08:00https://bevisy.github.io/p/llm-terminology-06-parallelism/2026-07-27T10:15:00+08:00https://bevisy.github.io/tags/moe/2026-07-27T10:15:00+08:00https://bevisy.github.io/tags/pipeline-parallelism/2026-07-27T10:15:00+08:00https://bevisy.github.io/tags/tensor-parallelism/2026-07-27T10:15:00+08:00https://bevisy.github.io/tags/zero/2026-07-27T10:15:00+08:00https://bevisy.github.io/tags/flash-attention/2026-07-27T10:00:00+08:00https://bevisy.github.io/p/llm-terminology-05-inference-optimization/2026-07-27T10:00:00+08:00https://bevisy.github.io/tags/pagedattention/2026-07-27T10:00:00+08:00https://bevisy.github.io/tags/speculative-decoding/2026-07-27T10:00:00+08:00https://bevisy.github.io/tags/deepseek-r1/2026-07-27T09:45:00+08:00https://bevisy.github.io/tags/dpo/2026-07-27T09:45:00+08:00https://bevisy.github.io/tags/grpo/2026-07-27T09:45:00+08:00https://bevisy.github.io/p/llm-terminology-04-rlhf-grpo/2026-07-27T09:45:00+08:00https://bevisy.github.io/tags/rlhf/2026-07-27T09:45:00+08:00https://bevisy.github.io/tags/deepseek/2026-07-27T09:30:00+08:00https://bevisy.github.io/p/llm-terminology-03-moe-residual/2026-07-27T09:30:00+08:00https://bevisy.github.io/tags/mhc/2026-07-27T09:30:00+08:00https://bevisy.github.io/tags/rope/2026-07-27T09:30:00+08:00https://bevisy.github.io/tags/kda/2026-07-27T09:15:00+08:00https://bevisy.github.io/tags/linear-attention/2026-07-27T09:15:00+08:00https://bevisy.github.io/p/llm-terminology-02-linear-hybrid-attention/2026-07-27T09:15:00+08:00https://bevisy.github.io/tags/minimax/2026-07-27T09:15:00+08:00https://bevisy.github.io/tags/qk-norm/2026-07-27T09:15:00+08:00https://bevisy.github.io/tags/attention/2026-07-27T09:00:00+08:00https://bevisy.github.io/tags/gqa/2026-07-27T09:00:00+08:00https://bevisy.github.io/tags/kv-cache/2026-07-27T09:00:00+08:00https://bevisy.github.io/p/llm-terminology-01-attention-mha-mla/2026-07-27T09:00:00+08:00https://bevisy.github.io/tags/mla/2026-07-27T09:00:00+08:00https://bevisy.github.io/p/llm-terminology-series-guide/2026-07-27T08:45:00+08:00https://bevisy.github.io/tags/deepspec/2026-07-22T18:00:00+08:00https://bevisy.github.io/p/speculative-decoding-deepspec-analysis/2026-07-22T18:00:00+08:00https://bevisy.github.io/tags/kimi/2026-07-21T22:30:00+08:00https://bevisy.github.io/p/kimi-k3-architecture-innovation/2026-07-21T22:30:00+08:00https://bevisy.github.io/p/kata-containers-gpu-support/2022-06-21T23:14:52+08:00https://bevisy.github.io/tags/kata-containers/2022-06-21T23:14:52+08:00https://bevisy.github.io/categories/linux/2022-06-21T23:14:52+08:00https://bevisy.github.io/categories/ubuntu/2022-06-21T23:14:52+08:00https://bevisy.github.io/p/close-swap-on-ubuntu-20-04/2021-05-25T13:55:24+08:00https://bevisy.github.io/tags/skill/2021-05-25T13:55:24+08:00https://bevisy.github.io/p/linux-loop-device-block-simulation/2021-04-02T16:37:51+08:00https://bevisy.github.io/tags/containerd/2021-01-11T13:56:02+08:00https://bevisy.github.io/p/install-kubernetes-1-20-1-and-containerd-1-4-3-on-ubuntu-with-zfs/2021-01-11T13:56:02+08:00https://bevisy.github.io/tags/kubeadm/2021-01-11T13:56:02+08:00https://bevisy.github.io/tags/kubernetes/2021-01-11T13:56:02+08:00https://bevisy.github.io/p/burn-the-operating-system-installation-disk-on-mac/2021-01-06T19:22:16+08:00https://bevisy.github.io/tags/iso/2021-01-06T19:22:16+08:00https://bevisy.github.io/tags/linux/2021-01-06T19:22:16+08:00https://bevisy.github.io/tags/macbook/2021-01-06T19:22:16+08:00https://bevisy.github.io/about/2021-01-06T00:00:00+00:00https://bevisy.github.io/page/2021-01-06T00:00:00+00:00https://bevisy.github.io/p/install-tigervnc-server-on-ubuntu-20-04/2020-07-31T11:47:14+08:00https://bevisy.github.io/tags/vnc/2020-07-31T11:47:14+08:00https://bevisy.github.io/p/install-wechat-client-on-ubuntu-20-04/2020-07-29T11:16:31+08:00https://bevisy.github.io/tags/wechat/2020-07-29T11:16:31+08:00https://bevisy.github.io/p/ubuntu-20-04-display-resolution/2020-07-27T10:24:29+08:00https://bevisy.github.io/tags/kata/2020-07-25T23:06:12+08:00https://bevisy.github.io/p/kata-containers-compile-and-installed/2020-07-25T23:06:12+08:00https://bevisy.github.io/categories/katacontainers/2020-07-25T23:06:12+08:00https://bevisy.github.io/p/compile-qemu-on-ubuntu-20-04/2020-07-24T22:21:51+08:00https://bevisy.github.io/tags/qemu/2020-07-24T22:21:51+08:00https://bevisy.github.io/p/the-skills-of-vim/2020-07-24T15:02:12+08:00https://bevisy.github.io/tags/vim/2020-07-24T15:02:12+08:00https://bevisy.github.io/p/compile-linux-kernel-on-ubuntu-20-04/2020-07-24T00:41:59+08:00https://bevisy.github.io/tags/kernel/2020-07-24T00:41:59+08:00https://bevisy.github.io/tags/zsh/2020-07-18T12:14:33+08:00https://bevisy.github.io/p/zsh-and-oh-my-zsh-installation-summary/2020-07-18T12:14:33+08:00https://bevisy.github.io/tags/netdata/2020-01-21T15:56:21+08:00https://bevisy.github.io/tags/nginx/2020-01-21T15:56:21+08:00https://bevisy.github.io/p/enable-https-access-for-netdata-via-nginx/2020-01-21T15:56:21+08:00https://bevisy.github.io/tags/ci/cd/2020-01-21T00:25:33+08:00https://bevisy.github.io/p/deploy-github-page-by-travis-ci/2020-01-21T00:25:33+08:00https://bevisy.github.io/archives/2019-05-28T00:00:00+00:00https://bevisy.github.io/search/