菜单
Run LLM inference tests with Qwen or other models. Use when testing model loading, inference, CUDA Graph, or generation quality.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Run matmul performance benchmarks. Use when user wants to measure TFLOPS, compare kernel performance, or verify correctness after code changes.
SM120 (Blackwell) CUDA expert. Use for wgmma/mma PTX inline assembly, TMA, narrow precision (FP4/FP6/FP8), and block-scaled GEMM development.
View and analyze build logs. Use when user wants to see build errors, check previous build output, or debug build failures.
Run all checks including lint, typecheck, and tests. Use before creating PRs or for comprehensive validation.
CUDA kernel development workflow. Use when writing, testing, or optimizing GPU kernels. Follows the Edit-Build-Validate-Benchmark-Commit cycle.
Run Ruff linter and formatter on Python code. Use before commits or when checking code style and quality issues.
| name | chat-test |
| description | Run LLM inference tests with Qwen or other models. Use when testing model loading, inference, CUDA Graph, or generation quality. |
Test LLM inference with PyGPUkit.
# Basic chat CLI
python examples/chat_cli.py --model /path/to/model
# Chat with thinking mode
python examples/chat_cli_thinking.py --model /path/to/model
# MoE model (Qwen3-8B etc.)
python examples/chat_cli_moe.py --model /path/to/model
Local test models:
/c/Users/y_har/.cache/huggingface/hub/models--Aratako--Qwen3-8B-ERP-v0.1//c/Users/y_har/.cache/huggingface/hub/models--TinyLlama--TinyLlama-1.1B-Chat-v1.0/# Enable CUDA Graph for decode
python examples/chat_cli_moe.py --model /path/to/model --use-cuda-graph