Loading...
┌───┐ │GPU│ └───┘
┌───┐─·─┌───┐ │GPU│─·─│GPU│ └───┘─·─└───┘
┌───┐─┌───┐ │GPU│─│GPU│ ├───┤─├───┤ │GPU│─│GPU│ └───┘─└───┘
| Feature | Free | Pro | Forge |
|---|---|---|---|
| CORE FEATURES | |||
| Smart Profiling | ✓Unlimited | ✓Unlimited | ✓Unlimited |
| Automated Benchmarking | ✓Unlimited | ✓Unlimited | ✓Unlimited |
| CodeLens Performance Metrics | ✓ | ✓ | ✓ |
| Local LLM Support (Ollama, vLLM) | ✓ | ✓ | ✓ |
| Automatic Kernel Fusion | ✓ | ✓ | ✓ |
| GPU Virtualization | ✓ | ✓ | ✓ |
| GPU EmulatorTest your kernels on A100, H100, and other GPUs without owning the hardware | ✗ | ✓ | ✓ |
| Multi-GPU Performance Comparison | ✗ | ✓6 GPU Max | ✓Unlimited |
| Natural Language Profiling | ✗ | ✓ | ✓ |
| Multi-GPU Execution Analysis | ✗ | Coming Soon | ✓ |
| AI FEATURES | |||
| Autocomplete Suggestions | ✓Limited | ✓Unlimited | ✓Unlimited |
| GPU-optimized Suggestions | ✗ | ✓ | ✓ |
| FORGE — KERNEL OPTIMIZATION | |||
| Model Optimizations | ✗ | ✗ | ✓ |
| Drop-in Replacement Kernels | ✗ | ✗ | ✓ |
| Dedicated Infrastructure | ✗ | ✗ | ✓ |
| On-Premise Deployment | ✗ | ✗ | ✓ |
┌───┐ │GPU│ └───┘
┌───┐─·─┌───┐ │GPU│─·─│GPU│ └───┘─·─└───┘
┌───┐─┌───┐ │GPU│─│GPU│ ├───┤─├───┤ │GPU│─│GPU│ └───┘─└───┘