ComfyUI/baselines/system_info.txt
Houde 0df0b0d613 fix: address CodeRabbit review comments on PR #14587
- utils.py: add device param to _load_safetensors_no_mmap, move tensors
  to target device instead of always returning CPU tensors
- utils.py: validate read length == expected bytes; raise RuntimeError
  on partial/corrupt reads instead of silently creating empty tensors
- utils.py: scope no-mmap fallback to sys.platform == win32 to avoid
  unnecessary overhead on Linux/Mac CUDA systems; add sys import
- baselines: replace hardcoded LvHHu username with %USERPROFILE% in
  startup commands for portability

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-23 14:51:22 +01:00

37 lines
1.0 KiB
Plaintext

=== ComfyUI ROCm Stable Baseline ===
Date: 2026-06-20
--- Python ---
Python: 3.12.10
--- PyTorch / ROCm ---
torch: 2.7.0a0+git3f903c3
CUDA avail: True
Device: AMD Radeon(TM) 8050S Graphics
VRAM (GB): 14.37
ROCm/HIP: 6.5.25205-c1c2abe52
--- torch packages ---
torch: 2.7.0a0+git3f903c3
torchvision: 0.22.0+9eb57cd
torchaudio: 2.6.0a0+1a8f621
--- ComfyUI ---
Version: 0.24.0
Backend: ROCm 6.5 (scottt/rocm-TheRock gfx1151 wheel)
Tested: SD1.5 512x512 20steps ~5 it/s, stable
--- Wheel sources (gfx1151 / Strix Halo) ---
torch: scottt/rocm-TheRock v6.5.0rc-pytorch/torch-2.7.0a0+git3f903c3-cp312-cp312-win_amd64.whl
torchvision: scottt/rocm-TheRock v6.5.0rc-pytorch/torchvision-0.22.0+9eb57cd-cp312-cp312-win_amd64.whl
torchaudio: scottt/rocm-TheRock v6.5.0rc-pytorch/torchaudio-2.6.0a0+1a8f621-cp312-cp312-win_amd64.whl
numpy: pinned to <2 (1.26.4) for wheel compatibility
--- Startup ---
cd %USERPROFILE%\ComfyUI
.\\venv\\Scripts\\activate
python main.py
--- Saved workflow ---
baselines/workflows/sd15_test_rocm_workflow.json