Skip to main content

external-cannbot-model-model-infer-kvcache

基于 PyTorch 框架的昇腾 NPU 模型推理 KVCache 优化技能。分析和优化 LLM 文本推理模型中的 KVCache 实现,包括连续缓存、分页注意力(Paged Attention)配合 FA 融合算子、MLA 压缩缓存。触发场景包括:KVCache 管理实现、paged attention、KV 压缩、FA 融合算子、OOM/性能问题、block_table/slot_mapping 构造。基于本仓库已有模型的 KVCache 实现经验,按模型类型和场景推荐最佳方案。

Jump to install

Source facts

Repository
ascend-ai-coding/awesome-ascend-skills
Last source activity
May 26, 2026 at 02:59
Detected SKILL.md language
Chinese
Stars
166
Forks
56

Install options

The review-first prompt is selected by default. You can switch to a direct command or download a local copy.

Review the source files

Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.