Features
CUDA kernel editor with AI autocomplete
Multi-DSL support: CUDA, Triton, CUTE, TileLang, PyTorch, Numba, Mojo
GPU emulator for 86+ GPU architectures
Real-time profiling with NCU integration
Automated kernel benchmarking and comparison
PTX/SASS assembly inspection
Register pressure and race detection
Multi-GPU performance comparison (up to 6 GPUs in Pro)
Custom agents with skills and MCP integrations
Natural language profiling queries
Forge CLI for automatic kernel optimization (CUDA/Triton generation)
Local LLM support (Ollama, vLLM, LM Studio)
Stable SSH remote GPU workflows
Performance trace recording and insights
Network request analysis and inspection
Console message reading with source-mapped stack traces
Puppeteer-based automation with auto-wait
Slim mode for basic browser tasks
CLI usage without MCP client
Optional CrUX API integration for field data
Usage statistics with opt-out
Update checks via npm (configurable)
Multi-account Chrome support
Gemini integration via extension
Source-mapped stack traces in console output
Auto-wait for action results
