https://weigao.cc/https://weigao.cc/ai-systems/https://weigao.cc/ai-systems/agentic-infrastructure/https://weigao.cc/ai-systems/agentic-infrastructure/openclaw-guide/https://weigao.cc/ai-systems/AMX/https://weigao.cc/ai-systems/AMX/openvino/https://weigao.cc/ai-systems/distributed-training/https://weigao.cc/ai-systems/distributed-training/gavel/https://weigao.cc/ai-systems/distributed-training/megatron_parallel/https://weigao.cc/ai-systems/distributed-training/nccl-test/https://weigao.cc/ai-systems/gpu-computing/https://weigao.cc/ai-systems/gpu-computing/cuda-agent/https://weigao.cc/ai-systems/gpu-computing/gpu_arch/https://weigao.cc/ai-systems/gpu-computing/gpu_communication/https://weigao.cc/ai-systems/gpu-computing/ptx/https://weigao.cc/ai-systems/gpu-computing/SAC%20-%20ISCA%2023/https://weigao.cc/ai-systems/llm-inference/https://weigao.cc/ai-systems/llm-inference/00-full-stack-synthesis/https://weigao.cc/ai-systems/llm-inference/01-kv-cache/https://weigao.cc/ai-systems/llm-inference/02-compute-vs-memory-bound/https://weigao.cc/ai-systems/llm-inference/03-quantization/https://weigao.cc/ai-systems/llm-inference/04-batching-scheduling/https://weigao.cc/ai-systems/llm-inference/05-speculative-decoding/https://weigao.cc/ai-systems/llm-inference/06-inference-engines/https://weigao.cc/ai-systems/llm-inference/agentic-infra-inference-optimization/https://weigao.cc/ai-systems/llm-inference/causal-attention-kv-hit-area/https://weigao.cc/ai-systems/llm-inference/chunked-prefill-deep-dive/https://weigao.cc/ai-systems/llm-inference/csa-hca-attention/https://weigao.cc/ai-systems/llm-inference/deepseek-mla/https://weigao.cc/ai-systems/llm-inference/deepseek-v3-technical-report-bilingual-notes/https://weigao.cc/ai-systems/llm-inference/dspark-vs-mtp/https://weigao.cc/ai-systems/llm-inference/fp4-fp8-quantization/https://weigao.cc/ai-systems/llm-inference/gdn-chunked-prefill/https://weigao.cc/ai-systems/llm-inference/inference-frameworks-2026/https://weigao.cc/ai-systems/llm-inference/kv-cache-hit-ratio-tpm-correction-model/https://weigao.cc/ai-systems/llm-inference/moe-inference/https://weigao.cc/ai-systems/llm-inference/prefill-trace-worker-dsa-mla/https://weigao.cc/ai-systems/llm-inference/simulator-modeling-guide/https://weigao.cc/ai-systems/llm-inference/token-flow-hidden-state/https://weigao.cc/ai-systems/profiling/https://weigao.cc/ai-systems/profiling/agentic-awp/https://weigao.cc/ai-systems/profiling/AI%20Profiling/https://weigao.cc/ai-systems/profiling/awp-breakdown-summary/https://weigao.cc/ai-systems/profiling/cprof_cpp/https://weigao.cc/ai-systems/profiling/critical_path/https://weigao.cc/ai-systems/profiling/ft-vs-vllm-sglang-comparison/https://weigao.cc/ai-systems/profiling/gpu-trace-analysis/https://weigao.cc/ai-systems/profiling/h20-batch-diagnosis/https://weigao.cc/ai-systems/profiling/hta/https://weigao.cc/ai-systems/profiling/llm-inference-optimization-summary/https://weigao.cc/ai-systems/profiling/mi308x-kernel-launch-bound-analysis/https://weigao.cc/ai-systems/profiling/nvtx/https://weigao.cc/ai-systems/profiling/profiling-to-simulation-evidence-chain/https://weigao.cc/ai-systems/profiling/Temporal%20Breakdown/https://weigao.cc/ai-systems/reasoning/https://weigao.cc/ai-systems/reasoning/01-what-is-ai-reasoning/https://weigao.cc/ai-systems/reasoning/02-reasoning-models-agents-and-long-tasks/https://weigao.cc/ai-systems/reasoning/03-rag-memory-finetuning-and-distillation/https://weigao.cc/ai-systems/training-frameworks/https://weigao.cc/ai-systems/training-frameworks/Dynamic%20Batching/https://weigao.cc/ai-systems/training-frameworks/stage2/https://weigao.cc/cpu-gpu/https://weigao.cc/cpu-gpu/arm-architecture/https://weigao.cc/cpu-gpu/arm-architecture/arm_inline_assembly/https://weigao.cc/cpu-gpu/arm-architecture/arm_ins/https://weigao.cc/cpu-gpu/cpu-architecture/https://weigao.cc/cpu-gpu/cpu-architecture/instruction-sets/https://weigao.cc/cpu-gpu/cpu-architecture/instruction-sets/amx/https://weigao.cc/cpu-gpu/cpu-architecture/instruction-sets/x86_inst/https://weigao.cc/cpu-gpu/cpu-architecture/memory-systems/https://weigao.cc/cpu-gpu/cpu-architecture/memory-systems/cache/https://weigao.cc/cpu-gpu/cpu-architecture/memory-systems/memory_va_page/https://weigao.cc/cpu-gpu/cpu-architecture/memory-systems/MMU/https://weigao.cc/cpu-gpu/cpu-architecture/memory-systems/numa_socket/https://weigao.cc/cpu-gpu/cpu-architecture/pipeline-performance/https://weigao.cc/cpu-gpu/cpu-architecture/pipeline-performance/ibs/https://weigao.cc/cpu-gpu/cpu-architecture/pipeline-performance/pipline/https://weigao.cc/fundamentals/https://weigao.cc/fundamentals/algorithms/https://weigao.cc/fundamentals/algorithms/backtrack/https://weigao.cc/fundamentals/algorithms/binary_search/https://weigao.cc/fundamentals/algorithms/binary_tree/https://weigao.cc/fundamentals/algorithms/data_struct/https://weigao.cc/fundamentals/algorithms/data_struct/hashmap/https://weigao.cc/fundamentals/algorithms/data_struct/linkedlist/https://weigao.cc/fundamentals/algorithms/data_struct/readme/https://weigao.cc/fundamentals/algorithms/data_struct/stack/https://weigao.cc/fundamentals/algorithms/data_struct/string/https://weigao.cc/fundamentals/algorithms/data_struct/tree/https://weigao.cc/fundamentals/algorithms/dfs_bfs/https://weigao.cc/fundamentals/algorithms/dp/https://weigao.cc/fundamentals/algorithms/lcs/https://weigao.cc/fundamentals/algorithms/package/https://weigao.cc/fundamentals/algorithms/presum/https://weigao.cc/fundamentals/algorithms/slide_window/https://weigao.cc/fundamentals/algorithms/snappet/https://weigao.cc/fundamentals/algorithms/sort/https://weigao.cc/fundamentals/programming-languages/https://weigao.cc/fundamentals/programming-languages/java/https://weigao.cc/fundamentals/programming-languages/java/android/https://weigao.cc/fundamentals/programming-languages/java/android/adb/https://weigao.cc/fundamentals/programming-languages/java/android/binder_01/https://weigao.cc/fundamentals/programming-languages/java/android/binder_02/https://weigao.cc/fundamentals/programming-languages/java/android/binder/https://weigao.cc/fundamentals/programming-languages/java/android/ipc/https://weigao.cc/fundamentals/programming-languages/java/android/parcel/https://weigao.cc/fundamentals/programming-languages/java/art/https://weigao.cc/fundamentals/programming-languages/java/art/art_create/https://weigao.cc/fundamentals/programming-languages/java/art/art_dex2oat/https://weigao.cc/fundamentals/programming-languages/java/art/art_jni/https://weigao.cc/fundamentals/programming-languages/java/art/gc_art_01/https://weigao.cc/fundamentals/programming-languages/java/jvm_art/https://weigao.cc/fundamentals/programming-languages/java/jvm/https://weigao.cc/fundamentals/programming-languages/java/jvm/01_jvm_memory/https://weigao.cc/fundamentals/programming-languages/java/jvm/gc_g1/https://weigao.cc/fundamentals/programming-languages/java/jvm/jvm_inst/https://weigao.cc/fundamentals/programming-languages/java/jvm/reflection/https://weigao.cc/fundamentals/programming-languages/python/https://weigao.cc/fundamentals/programming-languages/python/language/https://weigao.cc/fundamentals/programming-languages/python/language/coroutines/https://weigao.cc/fundamentals/programming-languages/python/language/crontab/https://weigao.cc/fundamentals/programming-languages/python/language/effective-python/https://weigao.cc/fundamentals/programming-languages/python/language/hash/https://weigao.cc/fundamentals/programming-languages/python/language/io/https://weigao.cc/fundamentals/programming-languages/python/language/itertools/https://weigao.cc/fundamentals/programming-languages/python/language/log/https://weigao.cc/fundamentals/programming-languages/python/language/pip/https://weigao.cc/fundamentals/programming-languages/python/language/py-data-struct/https://weigao.cc/fundamentals/programming-languages/python/language/py-file/https://weigao.cc/fundamentals/programming-languages/python/language/pytest/https://weigao.cc/fundamentals/programming-languages/python/language/python_c/https://weigao.cc/fundamentals/programming-languages/python/language/python-function/https://weigao.cc/fundamentals/programming-languages/python/language/python-oo/https://weigao.cc/fundamentals/programming-languages/python/tools/https://weigao.cc/fundamentals/programming-languages/python/tools/py-tools/https://weigao.cc/fundamentals/programming-languages/python/tools/virtualenv/https://weigao.cc/graph/https://weigao.cc/linux/https://weigao.cc/linux/commands-tools/https://weigao.cc/linux/commands-tools/command/https://weigao.cc/linux/educational/https://weigao.cc/linux/educational/xv6/https://weigao.cc/linux/kernel/https://weigao.cc/linux/kernel/internals/https://weigao.cc/linux/kernel/internals/BL31/https://weigao.cc/linux/kernel/internals/notifier/https://weigao.cc/linux/kernel/internals/pthread/https://weigao.cc/linux/kernel/internals/THP/https://weigao.cc/linux/kernel/scheduling/https://weigao.cc/linux/kernel/scheduling/idle_tick/https://weigao.cc/linux/kernel/scheduling/idle/https://weigao.cc/linux/kernel/scheduling/rcu/https://weigao.cc/linux/kernel/subsystems/https://weigao.cc/linux/kernel/subsystems/i2c/https://weigao.cc/linux/kernel/subsystems/thermal_init_h/https://weigao.cc/linux/kernel/subsystems/thermal_init/https://weigao.cc/linux/kernel/subsystems/thermal/https://weigao.cc/linux/system-administration/https://weigao.cc/linux/system-administration/apt/https://weigao.cc/linux/system-programming/https://weigao.cc/linux/system-programming/c-pointer/https://weigao.cc/linux/system-programming/cmake_makefile/https://weigao.cc/linux/system-programming/cmake/https://weigao.cc/linux/system-programming/linkers_loaders/https://weigao.cc/linux/system-programming/size_t/https://weigao.cc/mermaid-test/https://weigao.cc/more/https://weigao.cc/series/https://weigao.cc/tags/https://weigao.cc/tags/%E9%AB%98%E6%80%A7%E8%83%BD%E9%80%9A%E4%BF%A1/https://weigao.cc/tags/adb/https://weigao.cc/tags/agent/https://weigao.cc/tags/ai/https://weigao.cc/tags/ai%20gateway/https://weigao.cc/tags/ai%20infrastructure/https://weigao.cc/tags/algorithm/https://weigao.cc/tags/amd/https://weigao.cc/tags/android/https://weigao.cc/tags/api/https://weigao.cc/tags/arm/https://weigao.cc/tags/attention/https://weigao.cc/tags/awp/https://weigao.cc/tags/awq/https://weigao.cc/tags/backend/https://weigao.cc/tags/batch-analysis/https://weigao.cc/tags/batching/https://weigao.cc/tags/binary_search/https://weigao.cc/tags/binary%20tree/https://weigao.cc/tags/binder/https://weigao.cc/tags/blog/https://weigao.cc/tags/breakdown/https://weigao.cc/tags/bug%20log/https://weigao.cc/tags/c-cpp/https://weigao.cc/tags/c++/https://weigao.cc/tags/cache/https://weigao.cc/tags/chunked-prefill/https://weigao.cc/tags/claude%20code/https://weigao.cc/tags/cloud/https://weigao.cc/tags/cluster/https://weigao.cc/tags/codelife/https://weigao.cc/tags/computer%20architecture/https://weigao.cc/tags/continuous%20batching/https://weigao.cc/tags/cpu/https://weigao.cc/tags/critical%20path/https://weigao.cc/tags/csi/https://weigao.cc/tags/cuda/https://weigao.cc/tags/cv/https://weigao.cc/tags/database/https://weigao.cc/tags/decode/https://weigao.cc/tags/deep-learning/https://weigao.cc/tags/deeplearning/https://weigao.cc/tags/deepseek/https://weigao.cc/tags/diagnosis/https://weigao.cc/tags/disaggregated-serving/https://weigao.cc/tags/distillation/https://weigao.cc/tags/distributed-inference/https://weigao.cc/tags/distributed-training/https://weigao.cc/tags/distributed%20training/https://weigao.cc/tags/docker/https://weigao.cc/tags/dotfiles/https://weigao.cc/tags/dp/https://weigao.cc/tags/draft%20model/https://weigao.cc/tags/dspark/https://weigao.cc/tags/dwarf/https://weigao.cc/tags/dynamic%20batching/https://weigao.cc/tags/eagle/https://weigao.cc/tags/ebpf/https://weigao.cc/tags/expert-parallelism/https://weigao.cc/tags/figures/https://weigao.cc/tags/file/https://weigao.cc/tags/fine-tuning/https://weigao.cc/tags/flash-attention/https://weigao.cc/tags/flashattention/https://weigao.cc/tags/fp4/https://weigao.cc/tags/fp8/https://weigao.cc/tags/frameworks/https://weigao.cc/tags/frontend/https://weigao.cc/tags/gc/https://weigao.cc/tags/gdn/https://weigao.cc/tags/git/https://weigao.cc/tags/gptq/https://weigao.cc/tags/gpu-efficiency/https://weigao.cc/tags/gpu-kernel/https://weigao.cc/tags/gpu-optimization/https://weigao.cc/tags/gpu-profiling/https://weigao.cc/tags/gpu/https://weigao.cc/tags/h20/https://weigao.cc/tags/heterogeneous/https://weigao.cc/tags/hidden-state/https://weigao.cc/tags/hip/https://weigao.cc/tags/html-diagram/https://weigao.cc/tags/http/https://weigao.cc/tags/huawei/https://weigao.cc/tags/inference-framework/https://weigao.cc/tags/inference/https://weigao.cc/tags/inference%20engine/https://weigao.cc/tags/int4/https://weigao.cc/tags/int8/https://weigao.cc/tags/intel/https://weigao.cc/tags/interactive/https://weigao.cc/tags/isca/https://weigao.cc/tags/java/https://weigao.cc/tags/javascript/https://weigao.cc/tags/jvm/https://weigao.cc/tags/kernel-launch/https://weigao.cc/tags/kernel/https://weigao.cc/tags/kv-cache/https://weigao.cc/tags/kv%20cache/https://weigao.cc/tags/latex/https://weigao.cc/tags/lcs/https://weigao.cc/tags/leetcode/https://weigao.cc/tags/linux/https://weigao.cc/tags/llm-inference/https://weigao.cc/tags/llm/https://weigao.cc/tags/lm-head/https://weigao.cc/tags/macos/https://weigao.cc/tags/medusa/https://weigao.cc/tags/memory-modeling/https://weigao.cc/tags/memory%20management/https://weigao.cc/tags/mi308x/https://weigao.cc/tags/mla/https://weigao.cc/tags/moe/https://weigao.cc/tags/mtp/https://weigao.cc/tags/multi-agent/https://weigao.cc/tags/multi-chip/https://weigao.cc/tags/networks/https://weigao.cc/tags/nginx/https://weigao.cc/tags/node.js/https://weigao.cc/tags/nvfp4/https://weigao.cc/tags/observability/https://weigao.cc/tags/ohos/https://weigao.cc/tags/openclaw/https://weigao.cc/tags/optimization/https://weigao.cc/tags/other/https://weigao.cc/tags/others/https://weigao.cc/tags/page/https://weigao.cc/tags/pagedattention/https://weigao.cc/tags/paper/https://weigao.cc/tags/parallel%20computing/https://weigao.cc/tags/perf/https://weigao.cc/tags/perfetto/https://weigao.cc/tags/performance-analysis/https://weigao.cc/tags/performance/https://weigao.cc/tags/performance%20analysis/https://weigao.cc/tags/prefill/https://weigao.cc/tags/profiling/https://weigao.cc/tags/projects/https://weigao.cc/tags/ptx/https://weigao.cc/tags/python/https://weigao.cc/tags/pytorch/https://weigao.cc/tags/quantization/https://weigao.cc/tags/qwen3next/https://weigao.cc/tags/rag/https://weigao.cc/tags/reasoning/https://weigao.cc/tags/redis/https://weigao.cc/tags/research/https://weigao.cc/tags/rl/https://weigao.cc/tags/roofline/https://weigao.cc/tags/roofline%20model/https://weigao.cc/tags/rtp-llm/https://weigao.cc/tags/sass/https://weigao.cc/tags/scheduling/https://weigao.cc/tags/script/https://weigao.cc/tags/server/https://weigao.cc/tags/sglang/https://weigao.cc/tags/simt/https://weigao.cc/tags/simulation/https://weigao.cc/tags/simulator/https://weigao.cc/tags/sparse-attention/https://weigao.cc/tags/speculative-decoding/https://weigao.cc/tags/speculative%20decoding/https://weigao.cc/tags/spring/https://weigao.cc/tags/string/https://weigao.cc/tags/synthesis/https://weigao.cc/tags/systems/https://weigao.cc/tags/task%20dag/https://weigao.cc/tags/tcp-ip/https://weigao.cc/tags/tensorrt-llm/https://weigao.cc/tags/thoughts/https://weigao.cc/tags/thread/https://weigao.cc/tags/tlb/https://weigao.cc/tags/tooling/https://weigao.cc/tags/tools/https://weigao.cc/tags/tpm/https://weigao.cc/tags/trace/https://weigao.cc/tags/transformer/https://weigao.cc/tags/vim/https://weigao.cc/tags/vllm/https://weigao.cc/tags/vue.js/https://weigao.cc/tags/web%20framework/https://weigao.cc/tags/x86/https://weigao.cc/tags/yarn/https://weigao.cc/tags/zsh/https://weigao.cc/timeline/https://weigao.cc/toolbox/https://weigao.cc/toolbox/awp-profiling-api/https://weigao.cc/toolbox/cloud-server/https://weigao.cc/toolbox/cloud-server/design-pattern/https://weigao.cc/toolbox/cloud-server/Docker/https://weigao.cc/toolbox/cloud-server/gc/https://weigao.cc/toolbox/cloud-server/huawei_cloud/https://weigao.cc/toolbox/cloud-server/jvm_art/https://weigao.cc/toolbox/cloud-server/jvm/https://weigao.cc/toolbox/cloud-server/kernel/https://weigao.cc/toolbox/cloud-server/kvm/https://weigao.cc/toolbox/cloud-server/linux_os/https://weigao.cc/toolbox/cloud-server/nginx/https://weigao.cc/toolbox/cloud-server/openresty/https://weigao.cc/toolbox/cloud-server/snap/https://weigao.cc/toolbox/database/https://weigao.cc/toolbox/database/mongodb/https://weigao.cc/toolbox/database/mysql/https://weigao.cc/toolbox/database/peewee/https://weigao.cc/toolbox/database/redis/https://weigao.cc/toolbox/frameworks/https://weigao.cc/toolbox/frameworks/celery/https://weigao.cc/toolbox/frameworks/flask/https://weigao.cc/toolbox/frameworks/spring/https://weigao.cc/toolbox/frontend/https://weigao.cc/toolbox/frontend/chartsjs/https://weigao.cc/toolbox/frontend/css/https://weigao.cc/toolbox/frontend/jsnote/https://weigao.cc/toolbox/frontend/node_install/https://weigao.cc/toolbox/frontend/vue/https://weigao.cc/toolbox/networks/https://weigao.cc/toolbox/networks/epoll/https://weigao.cc/toolbox/networks/http/https://weigao.cc/toolbox/networks/networks/https://weigao.cc/toolbox/others/https://weigao.cc/toolbox/others/code_life/https://weigao.cc/toolbox/others/new/https://weigao.cc/toolbox/others/paper_report/https://weigao.cc/toolbox/others/soft_skills/https://weigao.cc/toolbox/others/thoughts-2018/https://weigao.cc/toolbox/others/worklog/https://weigao.cc/toolbox/others/zen_of_python/https://weigao.cc/toolbox/research-projects/https://weigao.cc/toolbox/research-projects/papers/https://weigao.cc/toolbox/research-projects/papers/vp_hpca14/https://weigao.cc/toolbox/research-projects/papers/vp_value_prediction/https://weigao.cc/toolbox/research-projects/projects/https://weigao.cc/toolbox/research-projects/projects/blog_plan/https://weigao.cc/toolbox/research-projects/projects/jekyll/https://weigao.cc/toolbox/research-projects/projects/kilo/https://weigao.cc/toolbox/research-projects/projects/qqbot/https://weigao.cc/toolbox/research-projects/projects/vueblog/https://weigao.cc/toolbox/research-projects/research/https://weigao.cc/toolbox/research-projects/research/ArrayTrack/https://weigao.cc/toolbox/research-projects/research/cnn/https://weigao.cc/toolbox/research-projects/research/csitool/https://weigao.cc/toolbox/research-projects/research/cvpr/https://weigao.cc/toolbox/research-projects/research/face_recognition/https://weigao.cc/toolbox/research-projects/research/information_theory/https://weigao.cc/toolbox/research-projects/research/latex/https://weigao.cc/toolbox/research-projects/research/mnist/https://weigao.cc/toolbox/research-projects/research/opencv/https://weigao.cc/toolbox/research-projects/research/RF-Pose/https://weigao.cc/toolbox/research-projects/research/splicer/https://weigao.cc/toolbox/research-projects/research/tensorflow/https://weigao.cc/toolbox/research-projects/research/tensorflowio/https://weigao.cc/toolbox/tools/https://weigao.cc/toolbox/tools/bat_win/https://weigao.cc/toolbox/tools/git/https://weigao.cc/toolbox/tools/html-diagram-test/https://weigao.cc/toolbox/tools/image-size-guide/https://weigao.cc/toolbox/tools/vim/https://weigao.cc/toolbox/tools/vps/https://weigao.cc/toolbox/tools/zsh-setup/