https://zhangchitc.github.io/tags/inference/Recent content in Inference on Chi's BlogHugoen-usWed, 04 Nov 2026 01:00:00 +0800https://zhangchitc.github.io/posts/flash-attention/Wed, 04 Nov 2026 01:00:00 +0800https://zhangchitc.github.io/posts/flash-attention/FlashAttention does every multiplication standard attention does, yet runs several times faster. We build it up step by step from the GPU memory hierarchy: kernel fusion, safe softmax, online softmax, and tiling.https://zhangchitc.github.io/posts/paged-attention/Tue, 03 Nov 2026 01:00:00 +0800https://zhangchitc.github.io/posts/paged-attention/Why serving LLMs fragments GPU memory, and how vLLM’s PagedAttention fixes it with OS-style paging: physical blocks, a block table, chained block hashes, and a walkthrough of how blocks are allocated, shared, freed and evicted.https://zhangchitc.github.io/posts/kv-cache-memory/Mon, 02 Nov 2026 17:00:00 +0800https://zhangchitc.github.io/posts/kv-cache-memory/We build the KV cache size formula one factor at a time, from single-head attention to multi-head, stacked layers and MQA/GQA, then check it against a real calculator: 13.73 GiB for 100,000 tokens on Qwen3-8B.https://zhangchitc.github.io/posts/kv-cache-vs-prompt-cache/Mon, 02 Nov 2026 01:00:00 +0800https://zhangchitc.github.io/posts/kv-cache-vs-prompt-cache/A prompt cache doesn’t store your last answer. We walk through prefill, decode and attention to see what the KV cache keeps, and how a prompt cache reuses it across requests.