mirror of
https://github.com/pytorch/pytorch.git
synced 2025-10-21 05:34:18 +08:00
Fixes #138532. This brings hipblas behavior in line with cublas behavior with respect to setting the workspace to an allocation from the caching allocator as well as the env var HIPBLAS_WORKSPACE_CONFIG. Pull Request resolved: https://github.com/pytorch/pytorch/pull/138791 Approved by: https://github.com/naromero77amd, https://github.com/eqy, https://github.com/malfet Co-authored-by: Nikita Shulga <2453524+malfet@users.noreply.github.com>