Repository navigation
Conversation
InvokeAI's release pins.json already publishes an xpu torch index, but the package only offered CPU, CUDA, ROCm and MPS, so Intel Arc users were recommended CPU. Add TorchIndex.Ipex, map it to the pins "xpu" key, and fall back to PyTorch's xpu index when an older tag has no pins entry. Tests cover the offered backends and the Intel Arc recommendation. Co-Authored-By: Claude Code <noreply@anthropic.com>
|
CLA Assistant Lite bot CLA Assistant bot All Contributors have signed the CLA. |
|
I have read the CLA Document and I hereby sign the CLA |
|
Related compatibility note found while testing this install on Fedora 44: #1788 (HuggingFace downloads behind Clash/mihomo fake-IP DNS). Kept separate from this PR because it is an InvokeAI downloader/SSRF configuration issue, not IPEX-specific. |
|
Looks right to me. The One likely problem: |
|
Thank you! |
Approved too early, sorry! The test fix from my earlier comment is still open: RecommendsIpexForIntelArc needs GetCompatibility() stubbed to return a RocmCompatibilityResult so it doesn't throw on Windows. Happy to approve once that's in.
Problem
Stability Matrix's InvokeAI package only offers CPU, CUDA, ROCm and MPS. On an Intel Arc GPU,
GetRecommendedTorchVersion()therefore falls back to CPU, even though InvokeAI publishes an XPU PyTorch index in itspins.json(torchIndexUrl.<platform>.xpu) and supports running on XPU.Fix
TorchIndex.IpextoInvokeAI.AvailableTorchIndices.pins.json, mapTorchIndex.Ipexto itsxpukey.xpupins entry.No behavior change for CPU, CUDA, ROCm or MPS.
Tests
dotnet test StabilityMatrix.Tests --filter InvokeAITorchIndexTests— 2 passed (IPEX offered, and recommended for Intel Arc).dotnet build StabilityMatrix.CoreandStabilityMatrix.Avalonia— 0 errors.--index https://download.pytorch.org/whl/xpu --index-strategy unsafe-first-match) resolves:invokeai==6.14.2torch==2.14.1+xputorchvision==0.29.1+xpulibcrypt.so.1for the bundled Python 3.10; that is an unrelated host prerequisite.)Notes
xpuentry inpins.json.🤖 Generated with Claude Code