viable/strict/1788603844: [cuBLAS] Always eagerly allocate cuBLAS(Lt) workspaces (#194311)
- PyTorch: 555 events in the last 90 days
- PyTorch: 549th Release in the last 90 days
- Previous: earlier the same day · trunk/8584bd71f1dbf9b1be692713f4f7c7f322bba923: [torchcomms hash update] update the pinned torchcomms hash (#195793)
What happened
authored with codex as discussed w/ @eellison , @ngimel ,~~~ just stashing this prototype here as performance doesn't look great on the hot path:~~~ AI-generated benchmark summary, provided for human review > > Benchmarked cached versus operation-scoped eager cuBLAS workspaces on an NVIDIA GB300, CC 10.3, CUDA 13.4. PyTorch was built for CC 10.0. Measurements are medians across five alternating cached/eager process…
Summary assembled by rule from the sources below