SkillsAdd

Source

ascend-ai-coding/awesome-ascend-skills

187 skills · 2.3K combined installs

Skills from this source

#
Skill
Source
8W Activity
Installs
1
npu-smi Huawei Ascend NPU npu-smi command reference. Use for device queries (health, temperature, power, memory, processes, E…
ascend-ai-coding/awesome-ascend-skills
104
2
ascend-docker Create Docker containers for Huawei Ascend NPU development with proper device mappings and volume mounts. Use when se…
ascend-ai-coding/awesome-ascend-skills
88
3
ascendc End-to-end AscendC custom operator development for Ascend NPU in an ascend-kernel (csrc/ops + build.sh + torch_npu Py…
ascend-ai-coding/awesome-ascend-skills
77
4
atc-model-converter Complete toolkit for Huawei Ascend NPU model conversion and end-to-end inference adaptation. Workflow 1 auto-discover…
ascend-ai-coding/awesome-ascend-skills
73
5
torch_npu 华为昇腾 Ascend Extension for PyTorch (torch_npu) 的环境检查、部署与能力指引。在用户使用 @torch_npu、昇腾 NPU、CANN、…
ascend-ai-coding/awesome-ascend-skills
71
6
hccl-test HCCL (Huawei Collective Communication Library) performance testing for Ascend NPU clusters. Use for testing distribut…
ascend-ai-coding/awesome-ascend-skills
67
7
vllm-ascend vLLM Ascend plugin for LLM inference serving on Huawei Ascend NPU. Use for offline batch inference, API server deploy…
ascend-ai-coding/awesome-ascend-skills
64
8
ais-bench AISBench Benchmark - AI model evaluation tool for Ascend NPU. Supports accuracy evaluation (service/local models on t…
ascend-ai-coding/awesome-ascend-skills
59
9
msmodelslim Huawei Ascend NPU model compression tool (msModelSlim). Use for LLM quantization (W4A8, W8A8, W8A8S, W8A16), MoE mode…
ascend-ai-coding/awesome-ascend-skills
44
10
skill-creator Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a…
ascend-ai-coding/awesome-ascend-skills
38
11
create-pr Creates GitHub pull requests with properly formatted titles that pass the check-pr-title CI validation. Use when crea…
ascend-ai-coding/awesome-ascend-skills
34
12
npu-docker-launcher Directly launch Docker containers on Ascend NPU servers for users. Collect requirements and execute docker run comman…
ascend-ai-coding/awesome-ascend-skills
34
13
remote-server-guide Guide for connecting to remote servers via SSH, managing containers, and executing commands remotely. Covers SSH conn…
ascend-ai-coding/awesome-ascend-skills
34
14
ascend-avi-vnpu 昇腾虚拟化实例（AVI）和vNPU管理技能。用于查询/设置AVI模式、管理vNPU实例（创建/销毁）、查询vNPU配置恢复状态等操作。支…
ascend-ai-coding/awesome-ascend-skills
33
15
ascend-dmi 当用户需要对华为昇腾 NPU 进行硬件层面的管理、测试或诊断时使用此 skill。典型场景： - 查看 NPU 卡的状态、温度、利用率 …
ascend-ai-coding/awesome-ascend-skills
33
16
wan-ascend-adaptation This skill provides comprehensive guidance for adapting Wan-series video generation models (Wan2.1/Wan2.2) from NVIDI…
ascend-ai-coding/awesome-ascend-skills
28
17
npu-op-benchmark 昇腾 NPU 单算子性能基准测试 Skill；当前版本只做现有环境检查、CANN 版本识别、用户确认后执行 benchmark，不负责修复或安…
ascend-ai-coding/awesome-ascend-skills
27
18
diffusers-ascend-env-setup HuggingFace Diffusers 环境配置指南，用于华为昇腾 NPU。覆盖 CANN 版本检测、PyTorch + torch_npu 安装、Diffusers 库安装…
ascend-ai-coding/awesome-ascend-skills
26
19
training-mfu-calculator 大模型训练MFU (Model FLOPs Utilization) 计算工具。在用户需要计算MFU、评估训练效率、分析模型性能、或提到FLOPs、吞吐量…
ascend-ai-coding/awesome-ascend-skills
26
20
diffusers-ascend-pipeline Diffusers Pipeline 推理指南，用于华为昇腾 NPU。覆盖环境预检、通用 Pipeline 推理（图像/视频模型）、内存优化（CPU offlo…
ascend-ai-coding/awesome-ascend-skills
25
21
diffusers-ascend-weight-prep Diffusers 模型权重准备工具，用于华为昇腾 NPU。支持从 HuggingFace 和 ModelScope 下载模型权重，以及基于 model_index.jso…
ascend-ai-coding/awesome-ascend-skills
25
22
triton-ascend-migration 将 GPU/CUDA Triton 算子迁移为 Triton-Ascend，或将 Python/PyTorch 算子改写为可在 Ascend NPU 上运行的 Triton-Ascend 实…
ascend-ai-coding/awesome-ascend-skills
24
23
ascend-opplugin 用于指导 Ascend C（CANN / xpu_kernel）算子开发完成后接入 PyTorch：与 torch_npu 对接、Host 侧注册与构建、Python 暴露与…
ascend-ai-coding/awesome-ascend-skills
23
24
mindspeed-llm-train-profiler 指导并自动化完成昇腾 NPU 上 MindSpeed-LLM 训练的 Profiling 数据采集。支持配置并运行带 Profiling 的模型训练，包括 CPU …
ascend-ai-coding/awesome-ascend-skills
22
25
profiling-analysis
ascend-ai-coding/awesome-ascend-skills
22
26
vllm-ascend-server Deploy vLLM inference services on Ascend NPU servers with automatic model detection and optimized configuration. Supp…
ascend-ai-coding/awesome-ascend-skills
19
27
vllm-bench-serve Interactive online benchmark orchestrator for vLLM inference services using `vllm bench serve`. Supports single bench…
ascend-ai-coding/awesome-ascend-skills
19
28
ai-for-science-ai4s-main AI for Science 昇腾 NPU 总入口 Skill，用于在用户只给出 AI for Science 需求、模型名、TensorFlow/Keras 项目或性能采集诉…
ascend-ai-coding/awesome-ascend-skills
18
29
mindspeed-llm-data-prep
ascend-ai-coding/awesome-ascend-skills
17
30
mindspeed-llm-env-setup MindSpeed-LLM 环境搭建指南，用于华为昇腾 NPU。覆盖 CANN 环境激活、PyTorch + torch_npu 安装、MindSpeed 加速库安装、Meg…
ascend-ai-coding/awesome-ascend-skills
17
31
mindspeed-llm-pipeline
ascend-ai-coding/awesome-ascend-skills
17
32
mindspeed-llm-training
ascend-ai-coding/awesome-ascend-skills
17
33
mindspeed-llm-weight-prep MindSpeed-LLM 权重转换指南，用于华为昇腾 NPU。覆盖 HuggingFace 到 Megatron 格式转换、Megatron 到 HuggingFace 反向转换…
ascend-ai-coding/awesome-ascend-skills
17
34
remote-npu-test Run NPU inference/training tests on a remote SSH server with vllm-ascend Docker container. Use when the user asks to …
ascend-ai-coding/awesome-ascend-skills
17
35
ai-for-science-ai4s-basic AI for Science 通用昇腾 NPU 模型迁移 Skill，适用于将基于 PyTorch、TensorFlow、vLLM 等框架的 CUDA 项目迁移到华为 Ascen…
ascend-ai-coding/awesome-ascend-skills
16
36
torch-npu-comm-test 通过 PyTorch torch.distributed 接口测试昇腾 NPU 通信算子性能。支持指定任意 tensor shape、dtype，使用 torchrun 启动，…
ascend-ai-coding/awesome-ascend-skills
16
37
ai-for-science-ai4s-profiling AI for Science 场景下的昇腾 NPU Profiling 采集与性能分析 Skill，用于在华为 Ascend NPU 上使用 torch_npu.profiler 采集 …
ascend-ai-coding/awesome-ascend-skills
15
38
ai-for-science-diffsbdd DiffSBDD 昇腾 NPU 迁移 Skill，适用于将基于等变扩散模型的结构化药物设计项目从 CUDA 迁移到华为 Ascend NPU，覆盖环境搭建…
ascend-ai-coding/awesome-ascend-skills
15
39
ai-for-science-ascend-tf-community 昇腾 TensorFlow Community 迁移适配 Skill，适用于将基于 TensorFlow 2.x 的模型原生部署到华为 Ascend NPU，而不经过 TF 到…
ascend-ai-coding/awesome-ascend-skills
14
40
ai-for-science-boltz2 Boltz2 蛋白质结构预测模型的昇腾 NPU 迁移与复现 Skill，适用于在华为 Ascend 910、910B、910C 上准备权重、适配 Lightning …
ascend-ai-coding/awesome-ascend-skills
14
41
ai-for-science-boltzgen BoltzGen 昇腾 NPU 迁移与复现 Skill，适用于在华为 Ascend NPU 上部署 BoltzGen 生成式蛋白设计与逆折叠流程，覆盖环境准备…
ascend-ai-coding/awesome-ascend-skills
14
42
ai-for-science-deepfri DeepFRI 的 TensorFlow 到 PyTorch 转换与昇腾 NPU 迁移 Skill，适用于蛋白质功能预测场景下的 TF 模型分析、PyTorch 重写、…
ascend-ai-coding/awesome-ascend-skills
14
43
ai-for-science-deepfri-tf-npu DeepFRI TensorFlow 原生昇腾 NPU 迁移 Skill，适用于不做 TF 到 PyTorch 转换、而是直接使用 TensorFlow 2.6.5 与 npu_devic…
ascend-ai-coding/awesome-ascend-skills
14
44
ai-for-science-generator GENERator DNA 序列生成模型的昇腾 NPU 迁移 Skill，适用于将基于 HuggingFace Transformers 的 Causal LM 从 CUDA 迁移到华…
ascend-ai-coding/awesome-ascend-skills
14
45
ai-for-science-oligoformer OligoFormer 昇腾 NPU 迁移 Skill，适用于将基于 PyTorch Transformer 的 siRNA 效能预测模型迁移到华为 Ascend NPU，覆盖环…
ascend-ai-coding/awesome-ascend-skills
14
46
ai-for-science-proteinbert ProteinBERT 昇腾 NPU 部署与迁移 Skill，适用于将 TensorFlow 或 Keras 版 ProteinBERT 转成基于 PyTorch 与 torch_npu 的实…
ascend-ai-coding/awesome-ascend-skills
14
47
ai-for-science-tf-to-pytorch TensorFlow 或 Keras 模型改写到 PyTorch 的通用 Skill，适用于在华为 Ascend NPU 或其他依赖 PyTorch 生态的平台上完成层级…
ascend-ai-coding/awesome-ascend-skills
14
48
external-gitcode-ascend-vLLM-ascend_FAQ_Generator 为 vLLM-ascend 项目构建自动化工作流，处理已关闭的Issue并生成Debug FAQ。Use when users want to process closed issues f…
ascend-ai-coding/awesome-ascend-skills
14
49
external-mindstudio-ascend-profiler-db-explorer 面向 Ascend PyTorch Profiler / msprof DB（如 ascend_pytorch_profiler*.db、msprof_*.db）的 SQL 分析技能。将自然语言问…
ascend-ai-coding/awesome-ascend-skills
14
50
external-mindstudio-cluster-fast-slow-rank-detector
ascend-ai-coding/awesome-ascend-skills
14
Page 1 · 187 total Next