https://yestino.com/entities/tf32-gemm-326fa7Every event involving TF32 GEMMenhttps://yestino.com/events/ciflow-b200-200788-rocm-round-gfx942-tf32-gemm-inputs-to-nea-f22666https://yestino.com/events/ciflow-b200-200788-rocm-round-gfx942-tf32-gemm-inputs-to-nea-f22666Sun, 18 Oct 2026 00:16:33 GMTSummary: Pull Request resolved: #200788 This diff adds opt-in round-to-nearest-even preprocessing for native FP32 GEMMs on AMD gfx942 so MI300 TF32 input conve… Sources: PyTorch Releaseshttps://yestino.com/events/ciflow-h100-200788-rocm-round-gfx942-tf32-gemm-inputs-to-nea-002efahttps://yestino.com/events/ciflow-h100-200788-rocm-round-gfx942-tf32-gemm-inputs-to-nea-002efaSun, 18 Oct 2026 00:16:33 GMTSummary: Pull Request resolved: #200788 This diff adds opt-in round-to-nearest-even preprocessing for native FP32 GEMMs on AMD gfx942 so MI300 TF32 input conve… Sources: PyTorch Releaseshttps://yestino.com/events/ciflow-rocm-mi300-200788-rocm-round-gfx942-tf32-gemm-inputs-d4d867https://yestino.com/events/ciflow-rocm-mi300-200788-rocm-round-gfx942-tf32-gemm-inputs-d4d867Sun, 18 Oct 2026 00:16:33 GMTSummary: Pull Request resolved: #200788 This diff adds opt-in round-to-nearest-even preprocessing for native FP32 GEMMs on AMD gfx942 so MI300 TF32 input conve… Sources: PyTorch Releases