Loading...
Loading...
Found 913 Skills
AscendC Operator Precision Evaluation. Generate a comprehensive precision test case set (≥30 cases) for the compiled and installed operator, run the tests and generate a precision verification report. Keywords: precision test, precision evaluation, precision report, accuracy, error analysis. After execution, YOU MUST display the overview, failure summary and key findings in the current conversation, and must not only attach the report path.
Evaluate the performance of Triton operators on Ascend NPU. It is used when users need to analyze operator performance bottlenecks, collect and compare operator performance using msprof/msprof op, diagnose Memory-Bound/Compute-Bound bottlenecks, measure hardware utilization metrics, and generate performance evaluation reports.
Deep Performance Optimization Skill for Triton Operators on Ascend NPU, dedicated to achieving the Triton operator performance improvement required by users. Core technologies include but are not limited to Unified Buffer (UB) capacity planning, multi-Tokens parallel processing, MTE/Vector pipeline parallelism, mask optimization, etc. This Skill must be triggered when the user mentions the following: performance optimization of Vector-type Triton operators on Ascend NPU.
Generate PyTorch-style interface documentation (README.md) for AscendC operators. Trigger scenarios: Use this when interface documentation needs to be generated after compilation and debugging are completed, or when the user mentions "generate operator documentation", "create README", "document operator", "help me write documentation" (in operator context), "operator documentation".
Generate interface documents for Triton operators of Ascend NPU. Used when users need to create or update interface documents for Triton operators of Ascend NPU. Core capabilities: (1) Generate standardized documents based on templates (2) Support the list of Ascend NPU product models (3) Provide specifications for operator parameter descriptions (4) Generate call example frameworks.
Python code refactoring skills, covering code smell identification, design pattern application, readability improvement, and practical experience. This skill is applicable when users request "refactor code", "refactor", "code optimization", "improve code quality", "code smell review", "apply design patterns", "enhance readability", or submit code review requests. It supports generating structured refactoring documents after refactoring completion ("output refactoring document", "generate refactoring report"). It includes practical patterns extracted from 20+ real refactoring PRs in the vllm-ascend repository.
AscendC Operator End-to-End Development Orchestrator. Used when users need to develop new operators, implement custom operators, or complete the full process from requirements to testing. Keywords: operator development, end-to-end, full process, workflow orchestration, new operator creation.
AscendC Operator Design Completion - Assist users in completing operator architecture design, interface definition, and performance planning. Use this skill when users mention operator design, operator development, tiling strategy, memory planning, AscendC kernel design, two-level tiling, inter-core splitting, or intra-core splitting.
Generate Triton operator requirement documents suitable for Ascend NPU. Used when users need to design new Triton operators, write operator requirement documents, or perform operator performance optimization design.
Debugging and Root Cause Localization for AscendC Operator Precision Issues. Used when operator precision tests fail (such as allclose failure, result deviation, all-zero/NaN output, etc.). Process: Error Distribution Analysis → Code Error-Prone Point Review → Experimental Isolation → printf/DumpTensor Instrumentation → Fix Verification. Keywords: precision debugging, precision issue, result inconsistency, error localization, allclose failure, output deviation, NaN, all-zero, precision debug.
HCCL (Huawei Collective Communication Library) performance testing for Ascend NPU clusters. Use for testing distributed communication bandwidth, verifying HCCL functionality, and benchmarking collective operations like AllReduce, AllGather. Covers MPI installation, multi-node pre-flight checks (SSH/CANN version/NPU health), and production testing workflows.
Create Docker containers for Huawei Ascend NPU development with proper device mappings and volume mounts. Use when setting up Ascend development environments in Docker, running CANN applications in containers, or creating isolated NPU development workspaces. Supports privileged mode (default), basic mode, and full mode with profiling/logging. Auto-detects available NPU devices.