Evan Carmen
687ce72dd3
Key changes based on HurbaLurba's DGX Spark research: - Remove --gpu-only flag (fights unified memory fabric) - Add --disable-pinned-memory, --force-fp16, --dont-upcast-attention - Add CUDA env vars for unified memory: CUDA_MANAGED_FORCE_DEVICE_ALLOC, PYTORCH_NO_CUDA_MEMORY_CACHING, OMP_NUM_THREADS=20 - Document unified memory architecture best practices - Add host-level GPU optimization instructions (clock locking, vboost) - Document SageAttention PR #297 status (merged then reverted) - Add credits section 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
23 lines
922 B
Bash
23 lines
922 B
Bash
# SparkyUI - ComfyUI for DGX Spark (Blackwell GB10)
|
|
# Copy this to .env and customize paths as needed
|
|
|
|
# Base path where your existing ComfyUI installation lives (for models)
|
|
COMFYUI_HOST_PATH=/path/to/your/ComfyUI
|
|
|
|
# Base path for SparkyUI data (custom_nodes, outputs, inputs, etc.)
|
|
SPARKYUI_DATA_PATH=/path/to/SparkyUI
|
|
|
|
# ComfyUI settings
|
|
COMFYUI_PORT=8188
|
|
|
|
# Optimized flags for Grace-Blackwell unified memory architecture
|
|
# Key: DON'T use --gpu-only - it fights the unified memory fabric
|
|
# --disable-pinned-memory: reduces overhead on unified fabric
|
|
# --force-fp16 + --fp16-*: enables SageAttention optimization
|
|
# --dont-upcast-attention: keeps attention in FP16 for speed
|
|
COMFYUI_FLAGS=--listen 0.0.0.0 --port 8188 --disable-pinned-memory --force-fp16 --fp16-unet --fp16-vae --fp16-text-enc --dont-upcast-attention
|
|
|
|
# Build refs (pin to specific commits/tags for reproducibility)
|
|
COMFYUI_REF=master
|
|
SAGEATTN_REF=main
|