https://blog.kkkzoz.top/ https://blog.kkkzoz.top/archive/ https://blog.kkkzoz.top/tags/ https://blog.kkkzoz.top/about/ https://blog.kkkzoz.top/posts/books/100-go-mistakes/chapter2-code-and-project-organization/ 2025-02-20 https://blog.kkkzoz.top/posts/books/100-go-mistakes/chapter4-control-structures/ 2025-02-20 https://blog.kkkzoz.top/posts/books/100-go-mistakes/chapter5/ 2025-03-03 https://blog.kkkzoz.top/posts/books/100-go-mistakes/chapter6/ 2025-03-04 https://blog.kkkzoz.top/posts/books/100-go-mistakes/chapter7/ 2025-03-07 https://blog.kkkzoz.top/posts/books/100-go-mistakes/chapter8-9/ 2025-03-19 https://blog.kkkzoz.top/posts/books/100-go-mistakes/chatpter3-data-types/ 2025-02-20 https://blog.kkkzoz.top/posts/books/build-a-large-language-model-from-scratch/ 2025-05-20 https://blog.kkkzoz.top/posts/books/design-data-intensive-applications/chapter-2-data-models-and-query-languages/ 2023-10-20 https://blog.kkkzoz.top/posts/books/design-data-intensive-applications/chapter-3-storage-and-retrieval/ 2023-10-20 https://blog.kkkzoz.top/posts/books/design-data-intensive-applications/chapter-4-encoding-and-evolution/ 2023-10-21 https://blog.kkkzoz.top/posts/books/design-data-intensive-applications/chapter-5-replication/ 2023-10-23 https://blog.kkkzoz.top/posts/books/design-data-intensive-applications/chapter-6-partioning/ 2023-10-24 https://blog.kkkzoz.top/posts/books/design-data-intensive-applications/chapter-7-transactions/ 2023-10-29 https://blog.kkkzoz.top/posts/books/design-data-intensive-applications/chapter-8-the-trouble-with-distributed-systems/ 2023-11-02 https://blog.kkkzoz.top/posts/books/design-data-intensive-applications/chapter-9-consistency-and-consensus/ 2023-11-13 https://blog.kkkzoz.top/posts/books/missing-semester/lecture-1/ 2024-10-09 https://blog.kkkzoz.top/posts/books/missing-semester/lecture-2/ 2024-10-11 https://blog.kkkzoz.top/posts/books/missing-semester/lecture-4/ 2024-10-15 https://blog.kkkzoz.top/posts/books/missing-semester/lecture-5/ 2024-10-17 https://blog.kkkzoz.top/posts/books/programming-rust/ 2024-02-10 https://blog.kkkzoz.top/posts/books/tips-and-guidance-for-writing/ 2025-03-31 https://blog.kkkzoz.top/posts/distributed/6-824-lab2b-research/ 2023-11-08 https://blog.kkkzoz.top/posts/distributed/about-cap/ 2023-11-06 https://blog.kkkzoz.top/posts/distributed/consistency-and-consensus/ 2023-11-07 https://blog.kkkzoz.top/posts/distributed/postgres-visibility-check-rules/ 2023-12-04 https://blog.kkkzoz.top/posts/distributed/redlock/ 2023-11-02 https://blog.kkkzoz.top/posts/distributed/transaction-anomalies/ 2024-03-31 https://blog.kkkzoz.top/posts/languages/go/common-mistakes/ 2025-04-23 https://blog.kkkzoz.top/posts/languages/go/errors/ 2025-02-04 https://blog.kkkzoz.top/posts/languages/go/profiling/ 2024-10-23 https://blog.kkkzoz.top/posts/languages/go/struct-and-interface/ 2025-01-28 https://blog.kkkzoz.top/posts/languages/go/testing/ 2024-01-21 https://blog.kkkzoz.top/posts/languages/java-threadlocal/ 2023-11-29 https://blog.kkkzoz.top/posts/languages/rust/100-exercises-to-learn-rust/ 2025-03-13 https://blog.kkkzoz.top/posts/languages/rust/rustlings/ 2024-12-26 https://blog.kkkzoz.top/posts/languages/rust/using-rust/ 2025-03-26 https://blog.kkkzoz.top/posts/misc/llm-generated-content/ 2025-08-08 https://blog.kkkzoz.top/posts/ml-systems/deep-learning-basic/ 2025-05-27 https://blog.kkkzoz.top/posts/ml-systems/ggml-with-cpp/ 2026-03-18 https://blog.kkkzoz.top/posts/ml-systems/gpu-kernels/tilelang-production-ready-ops/ 2026-08-17 https://blog.kkkzoz.top/posts/ml-systems/gpu-kernels/tilelang-programming-model/ 2026-08-18 https://blog.kkkzoz.top/posts/ml-systems/gpu-kernels/triton-builtin-tutorial/ 2026-01-07 https://blog.kkkzoz.top/posts/ml-systems/gpu-kernels/triton-notes-and-paradigms/ 2026-02-27 https://blog.kkkzoz.top/posts/ml-systems/math/matrix-math/ 2026-03-18 https://blog.kkkzoz.top/posts/ml-systems/math/probability-and-statistics/ 2026-03-18 https://blog.kkkzoz.top/posts/ml-systems/ml-compilers/overview/ 2026-08-11 https://blog.kkkzoz.top/posts/ml-systems/ml-compilers/piecewise-cuda-graph/ 2026-08-09 https://blog.kkkzoz.top/posts/ml-systems/ml-compilers/torch-compile-walkthrough/ 2026-10-20 https://blog.kkkzoz.top/posts/ml-systems/ml-compilers/vllm-torch-compile/ 2026-08-10 https://blog.kkkzoz.top/posts/ml-systems/numpy-notes/ 2025-05-26 https://blog.kkkzoz.top/posts/ml-systems/pytorch-notes/ 2026-01-15 https://blog.kkkzoz.top/posts/ml-systems/qwen3-5/ 2026-08-19 https://blog.kkkzoz.top/posts/ml-systems/sequence-modeling/linear-attention/ 2026-03-16 https://blog.kkkzoz.top/posts/ml-systems/sequence-modeling/lstm/ 2026-03-16 https://blog.kkkzoz.top/posts/ml-systems/sequence-modeling/mamba/ 2026-03-16 https://blog.kkkzoz.top/posts/ml-systems/sequence-modeling/rnn/ 2026-03-16 https://blog.kkkzoz.top/posts/papers/distributed-systems/bigtable/ 2023-10-30 https://blog.kkkzoz.top/posts/papers/distributed-systems/cap-twelve-years-later/ 2023-11-12 https://blog.kkkzoz.top/posts/papers/distributed-systems/chain-replication/ 2023-11-06 https://blog.kkkzoz.top/posts/papers/distributed-systems/chubby/ 2023-10-31 https://blog.kkkzoz.top/posts/papers/distributed-systems/mapreduce/ 2023-10-30 https://blog.kkkzoz.top/posts/papers/distributed-systems/paper-index/ 2025-08-01 https://blog.kkkzoz.top/posts/papers/distributed-systems/time-clocks-and-the-ordering/ 2023-11-04 https://blog.kkkzoz.top/posts/papers/distributed-systems/zab/ 2023-11-15 https://blog.kkkzoz.top/posts/papers/distributed-systems/zookeeper/ 2023-10-30 https://blog.kkkzoz.top/posts/papers/how-to-read-a-paper/ 2023-12-05 https://blog.kkkzoz.top/posts/papers/llm/3-model-speculative-decoding/ 2026-02-09 https://blog.kkkzoz.top/posts/papers/llm/a-dynamic-parallel-method-for-performance-optimization-on-hybrid-cpus/ 2025-11-11 https://blog.kkkzoz.top/posts/papers/llm/a-survey-of-resource-efficient-llm-and-multimodal-foundation-models/ 2025-08-21 https://blog.kkkzoz.top/posts/papers/llm/a-survey-on-efficient-inference-for-large-language-models/ 2025-07-20 https://blog.kkkzoz.top/posts/papers/llm/aiconfigurator-lightning-fast-configuration-optimization-for-multi-framework-llm-serving/ 2026-02-05 https://blog.kkkzoz.top/posts/papers/llm/awq-activation-aware-weight-quantization-for-llm-compression-and-acceleration/ 2025-07-28 https://blog.kkkzoz.top/posts/papers/llm/beyond-the-80-20-rule-high-entropy-minority-tokens-drive-effective-reinforcement-learning-for-llm-reasoning/ 2026-01-07 https://blog.kkkzoz.top/posts/papers/llm/cas-spec-cascade-adaptive-self-speculative-decoding-for-on-the-fly-lossless-inference-acceleration-of-llms/ 2026-02-07 https://blog.kkkzoz.top/posts/papers/llm/cascade-speculative-drafting-for-even-faster-llm-inference/ 2026-02-10 https://blog.kkkzoz.top/posts/papers/llm/deja-vu-contextual-sparsity-for-efficient-llms-at-inference-time/ 2025-08-04 https://blog.kkkzoz.top/posts/papers/llm/distserve-disaggregating-prefill-and-decoding-for-goodput-optimized-large-language-model-serving/ 2025-11-03 https://blog.kkkzoz.top/posts/papers/llm/draft-verify-lossless-large-language-model-acceleration-via-self-speculative-decoding/ 2026-02-08 https://blog.kkkzoz.top/posts/papers/llm/duoattention-efficient-long-context-llm-inference-with-retrieval-and-streaming-heads/ 2025-11-13 https://blog.kkkzoz.top/posts/papers/llm/dynamic-sparse-attention-on-mobile-socs/ 2025-11-11 https://blog.kkkzoz.top/posts/papers/llm/eagle-speculative-sampling-requires-rethinking-feature-uncertainty/ 2025-11-10 https://blog.kkkzoz.top/posts/papers/llm/edgellm-fast-on-device-llm-inference-with-speculative-decoding/ 2025-07-23 https://blog.kkkzoz.top/posts/papers/llm/edgemoe-empowering-sparse-large-language-models-on-mobile-devices/ 2025-08-24 https://blog.kkkzoz.top/posts/papers/llm/edgeshard-efficient-llm-inference-via-collaborative-edge-computing/ 2025-07-01 https://blog.kkkzoz.top/posts/papers/llm/efficient-memory-management-for-large-language-model-serving-with-pagedattention/ 2025-07-23 https://blog.kkkzoz.top/posts/papers/llm/efficient-streaming-language-models-with-attention-sinks/ 2025-11-13 https://blog.kkkzoz.top/posts/papers/llm/elms-elasticized-large-language-models-on-mobile-devices/ 2025-08-27 https://blog.kkkzoz.top/posts/papers/llm/entropy-adaptive-decoding-dynamic-model-switching-for-efficient-inference/ 2026-01-07 https://blog.kkkzoz.top/posts/papers/llm/estimating-llm-uncertainty-with-evidence/ 2026-02-02 https://blog.kkkzoz.top/posts/papers/llm/fast-on-device-llm-inference-with-npus/ 2025-08-04 https://blog.kkkzoz.top/posts/papers/llm/flexgen-high-throughput-generative-inference-of-large-language-models-with-a-single-gpu/ 2025-07-25 https://blog.kkkzoz.top/posts/papers/llm/flexprefill-a-context-aware-sparse-attention-mechanism-for-efficient-long-sequence-inference/ 2026-01-29 https://blog.kkkzoz.top/posts/papers/llm/h2o-heavy-hitter-oracle-for-efficient-generative-inference-of-large-language-models/ 2025-08-21 https://blog.kkkzoz.top/posts/papers/llm/heterollm-accelerating-large-language-model-inference-on-mobile-socs-with-heterogeneous-ai-accelerators/ 2025-08-24 https://blog.kkkzoz.top/posts/papers/llm/hierarchical-speculative-decoding-with-dynamic-windows-for-efficient-language-model-inference/ 2026-02-07 https://blog.kkkzoz.top/posts/papers/llm/ktransformers-deep-dive/ 2026-10-24 https://blog.kkkzoz.top/posts/papers/llm/kv-runahead-scalable-causal-llm-inference-by-parallel-key-value-cache-generation/ 2025-08-17 https://blog.kkkzoz.top/posts/papers/llm/kvcache-cache-in-the-wild-characterizing-and-optimizing-kvcache-cache-at-a-large-cloud-provider/ 2025-12-06 https://blog.kkkzoz.top/posts/papers/llm/layerskip-enabling-early-exit-inference-and-self-speculative-decoding/ 2026-02-09 https://blog.kkkzoz.top/posts/papers/llm/llm-as-a-system-service-on-mobile-devices/ 2025-08-18 https://blog.kkkzoz.top/posts/papers/llm/llm-in-a-flash-efficient-large-language-model-inference-with-limited-memory/ 2025-07-30 https://blog.kkkzoz.top/posts/papers/llm/llm-int8-8-bit-matrix-multiplication-for-transformers-at-scale/ 2025-08-12 https://blog.kkkzoz.top/posts/papers/llm/llm-preliminaries/ 2025-08-04 https://blog.kkkzoz.top/posts/papers/llm/lora-low-rank-adaptation-of-large-language-models/ 2025-07-25 https://blog.kkkzoz.top/posts/papers/llm/lserve-efficient-long-sequence-llm-serving-with-unified-sparse-attention/ 2025-11-15 https://blog.kkkzoz.top/posts/papers/llm/orca-a-distributed-serving-system-for-transformer-based-generative-models/ 2025-07-02 https://blog.kkkzoz.top/posts/papers/llm/paper-index/ 2025-07-28 https://blog.kkkzoz.top/posts/papers/llm/powerinfer-2-fast-large-language-model-inference-on-a-smartphone/ 2025-07-29 https://blog.kkkzoz.top/posts/papers/llm/powerinfer-fast-large-language-model-serving-with-a-consumer-grade-gpu/ 2025-07-28 https://blog.kkkzoz.top/posts/papers/llm/qserve-w4a8kv4-quantization-and-system-co-design-for-efficient-llm-serving/ 2025-11-16 https://blog.kkkzoz.top/posts/papers/llm/quest-query-aware-sparsity-for-efficient-long-context-llm-inference/ 2025-11-13 https://blog.kkkzoz.top/posts/papers/llm/r-stitch-dynamic-trajectory-stitching-for-efficient-reasoning/ 2026-02-02 https://blog.kkkzoz.top/posts/papers/llm/revati-transparent-gpu-free-time-warp-emulation-for-llm-serving/ 2026-02-05 https://blog.kkkzoz.top/posts/papers/llm/ring-attention-with-blockwise-transformers-for-near-infinite-context/ 2025-08-17 https://blog.kkkzoz.top/posts/papers/llm/scaling-up-on-device-llms-via-active-weight-swapping-between-dram-and-flash/ 2025-09-01 https://blog.kkkzoz.top/posts/papers/llm/serverlessllm-locality-enhanced-serverless-inference-for-large-language-models/ 2025-06-28 https://blog.kkkzoz.top/posts/papers/llm/sled-a-speculative-llm-decoding-framework-for-efficient-edge-serving/ 2025-12-07 https://blog.kkkzoz.top/posts/papers/llm/smallthinker-a-family-of-efficient-large-language-models-natively-trained-for-local-deployment/ 2025-08-25 https://blog.kkkzoz.top/posts/papers/llm/smoothquant-accurate-and-efficient-post-training-quantization-for-large-language-models/ 2025-11-16 https://blog.kkkzoz.top/posts/papers/llm/specinfer-accelerating-large-language-model-serving-with-tree-based-speculative-inference-and-verification/ 2025-07-25 https://blog.kkkzoz.top/posts/papers/llm/splitwise-efficient-generative-llm-inference-using-phase-splitting/ 2025-11-03 https://blog.kkkzoz.top/posts/papers/llm/sti-turbocharge-nlp-inference-at-the-edge-via-elastic-pipelining/ 2025-08-25 https://blog.kkkzoz.top/posts/papers/llm/striped-attention-faster-ring-attention-for-causal-transformers/ 2025-08-17 https://blog.kkkzoz.top/posts/papers/llm/swift-on-the-fly-self-speculative-decoding-for-llm-inference-acceleration/ 2026-02-08 https://blog.kkkzoz.top/posts/papers/llm/taming-throughput-latency-tradeoff-in-llm-inference-with-sarathi-serve/ 2025-11-01 https://blog.kkkzoz.top/posts/papers/llm/think-big-generate-quick-llm-to-slm-for-fast-autoregressive-decoding/ 2026-01-07 https://blog.kkkzoz.top/posts/papers/llm/token-level-routing-inference-system-for-edge-devices/ 2025-12-01 https://blog.kkkzoz.top/posts/papers/llm/tpi-llm-serving-70b-scale-llms-efficiently-on-low-resource-mobile-devices/ 2025-08-17 https://blog.kkkzoz.top/posts/papers/llm/xattention-block-sparse-attention-with-antidiagonal-scoring/ 2026-01-29 https://blog.kkkzoz.top/posts/papers/transactions/ad-hoc-transactions-in-web-applications/ 2023-11-30 https://blog.kkkzoz.top/posts/papers/transactions/cobra/ 2023-11-23 https://blog.kkkzoz.top/posts/papers/transactions/concurrency-control-as-a-service/ 2025-07-11 https://blog.kkkzoz.top/posts/papers/transactions/data-management-in-microservices/ 2024-04-15 https://blog.kkkzoz.top/posts/papers/transactions/epoxy/ 2023-11-22 https://blog.kkkzoz.top/posts/papers/transactions/grit/ 2023-12-08 https://blog.kkkzoz.top/posts/papers/transactions/omid-reloaded/ 2024-03-22 https://blog.kkkzoz.top/posts/papers/transactions/paper-index/ 2025-08-01 https://blog.kkkzoz.top/posts/papers/transactions/scalable-distributed-transactions-across-heterogeneous-stores/ 2023-12-09 https://blog.kkkzoz.top/posts/papers/transactions/sonata-multi-database-transactions-made-fast-and-serializable/ 2025-07-13 https://blog.kkkzoz.top/posts/papers/transactions/taking-omid-to-the-clouds/ 2024-03-25 https://blog.kkkzoz.top/posts/papers/transactions/towards-transaction-as-a-service/ 2024-01-22 https://blog.kkkzoz.top/posts/tools/aerospace/ 2024-12-24 https://blog.kkkzoz.top/posts/tools/chrome-plugins/ 2025-04-01 https://blog.kkkzoz.top/posts/tools/clang-on-apple/ 2025-09-12 https://blog.kkkzoz.top/posts/tools/cli-notes/ 2026-03-17 https://blog.kkkzoz.top/posts/tools/dev-operations/ 2025-04-17 https://blog.kkkzoz.top/posts/tools/docker-network/ 2025-03-29 https://blog.kkkzoz.top/posts/tools/git-essentials/ 2025-08-08 https://blog.kkkzoz.top/posts/tools/jujutsu/ 2025-04-04 https://blog.kkkzoz.top/posts/tools/log-levels/ 2024-05-13 https://blog.kkkzoz.top/posts/tools/macos-setup/ 2024-11-21 https://blog.kkkzoz.top/posts/tools/macos-shortcuts/ 2025-04-19 https://blog.kkkzoz.top/posts/tools/pass-the-wall/ 2025-03-30 https://blog.kkkzoz.top/posts/tools/server-management/ 2026-01-08 https://blog.kkkzoz.top/posts/tools/software-router/ 2026-01-05 https://blog.kkkzoz.top/posts/tools/sync-dot-files/ 2025-10-04 https://blog.kkkzoz.top/posts/tools/useful-websites/ 2025-05-19 https://blog.kkkzoz.top/posts/tools/vscode-essentials/ 2025-08-06 https://blog.kkkzoz.top/posts/tools/watchdog-in-openfaas/ 2024-08-25 https://blog.kkkzoz.top/posts/tools/windows-mouse-action-on-unix/ 2024-11-26 https://blog.kkkzoz.top/posts/tools/wsl2-mirrored-network/ 2023-11-25