Tsondo bb31f8b707 fix: per-device fp8/nvfp4 compute detection for multi-GPU setups ... supports_fp8_compute() and supports_nvfp4_compute() used the global is_nvidia() check which ignores the device argument, then defaulted to cuda:0 when device was None. In heterogeneous multi-GPU setups (e.g. RTX 5070 + RTX 3090 Ti) this causes the wrong GPU's compute capability to be checked, incorrectly disabling fp8 on capable devices. Replace the global is_nvidia() gate with per-device checks: - Default device=None to get_torch_device() explicitly - Early-return False for CPU/MPS devices - Use is_device_cuda(device) + torch.version.cuda instead of the global is_nvidia() Fixes #4589, relates to #4577, #12405 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>		2026-03-14 22:56:42 +01:00
..
folder_path_test.py
model_detection_test.py	Native LongCat-Image implementation (#12597)	2026-02-27 23:04:34 -05:00
model_management_test.py	fix: per-device fp8/nvfp4 compute detection for multi-GPU setups	2026-03-14 22:56:42 +01:00