Claude
46b9066bba
Handle old/low-VRAM GPUs and document nvidia-container-toolkit requirement
GPU tier table extended:
ultra ≥16 GB → SDXL (unchanged)
high 8-16 GB → SDXL (unchanged)
medium 4-8 GB → SD 2.x (unchanged)
legacy 2-4 GB → SD 1.5 (~1.7 GB fp16) ← new: GTX 970/1060/RX 580 etc.
minimal <2 GB → SD 1.5 + sequential CPU offload ← new: very old/integrated GPUs
gpu_detect.py:
- Detects CUDA compute capability (CC); fp16 disabled for CC < 6.0 (pre-Pascal)
- GpuInfo gains compute_capability and warnings fields
- _make_warnings() emits human-readable warnings for low VRAM and old CC
- model tier fallback updated from 'low' to 'legacy'
local_diffusion.py:
- minimal/legacy tiers use enable_sequential_cpu_offload() + enable_attention_slicing(1)
- target resolution per tier: ultra/high=1024, medium=768, legacy/minimal=512
- .to(device) skipped when sequential CPU offload is active
gpu_status.py:
- Response now includes compute_capability and warnings
docker-compose.gpu.yml:
- Full nvidia-container-toolkit install instructions in header comment
- nvidia-docker2 (legacy) fallback documented as comment block inline
- AMD ROCm swap-in instructions added
- GPU tier table documented in header
scripts/gpu_setup.py:
- Prints compute capability, fp16 status, tier, and model selection at startup
- Prints per-tier warnings (old CC, low VRAM)
https://claude.ai/code/session_01WVDg7amsy1TTtxvpku7bcM
2026-06-13 15:19:01 +00:00
..
2026-01-24 02:58:41 +00:00
2026-06-13 15:08:41 +00:00
2026-01-24 02:58:41 +00:00
2026-01-24 04:06:19 +00:00
2026-06-13 15:19:01 +00:00
2026-01-24 02:58:41 +00:00
2026-01-24 03:32:50 +00:00
2026-06-09 18:38:45 +00:00
2026-01-24 02:58:41 +00:00
2026-01-28 13:23:49 +00:00