Menu
Run LLM inference tests with Qwen or other models. Use when testing model loading, inference, CUDA Graph, or generation quality.
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Baseado na classificação ocupacional SOC
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