ZLUDA · Issues· 166 open
Open on GitHubLocally synced open issues (discussions stay on GitHub)
- #202
How to even test this under Linux?
Updated Sep 14, 2026 - #677
Can't open on i5-13500h
Updated Sep 11, 2026 - #513
Does not work with Meshroom 2025.1.0
Updated Sep 6, 2026 - #674
CUDA_ERROR_INSUFFICIENT_DRIVER (error 35) when using ZLUDA with ONNX Runtime
Updated Aug 25, 2026 - #673
MLX failing to load on Linux with CUDA 12 backend
Updated Aug 21, 2026 - #656
PhysX/32 bit TODO
Updated Aug 17, 2026 - #671
Unify 64-bit and 32-bit zluda.exe
help wantedUpdated Aug 16, 2026 - #660
Can't get PhysX working with Mirror's Edge
Updated Aug 15, 2026 - #655
Improve FP64 accuracy
help wantedUpdated Aug 11, 2026 - #653
Make zluda.exe more user-friendly
help wantedUpdated Aug 11, 2026 - #646
Hard crash (Access Violation 0xc0000005) during initialization on RX 9070 (RDNA 4 / gfx1201) with ROCm 7.1
Updated Aug 11, 2026 - #636
"llama.cpp abort:97: CUDA error" When Using LM Studio
Updated Aug 11, 2026 - #634
PyTorch torch.fft / torch.stft fail with CUFFT_NOT_SUPPORTED on Windows + HIP 7.13 + RX 7900 XTX
Updated Aug 11, 2026 - #627
CUDA_ERROR_NOT_FOUND in cuModuleGetFunction during PyTorch model.to(device) (YOLO11)
Updated Aug 11, 2026 - #622
llama.cpp with ZLUDA fails on Qwen3.5-35B-A3B-UD-Q4_K_XL model
Updated Aug 11, 2026