Rust Compiler Drops Legacy NVIDIA GPU Support in Upcoming Release
In a significant breaking change for GPU developers, the Rust team announced that version 1.97, scheduled for release on July 9, 2026, will increase the minimum requirements for the nvptx64-nvidia-cuda target. PTX outputs will now require PTX ISA version 7.0 (CUDA 11 driver or newer) and GPU compute capability 7.0 (Volta or later).
This move immediately renders all PTX artifacts incompatible with pre-Volta GPUs such as Maxwell and Pascal, as well as CUDA drivers from the CUDA 10 era and earlier. Developers relying on legacy hardware must stay on older Rust versions or update their target specifications.
“These changes are necessary to eliminate long-standing compiler defects and miscompilations that affected older architectures,” said a spokesperson for the Rust compiler team. “By focusing on modern NVIDIA hardware, we can improve correctness and performance for the vast majority of users.”
Background: Why the Baseline is Moving
Until now, Rust supported emitting PTX for a wide range of GPU architectures and PTX ISA versions. However, in practice, several defects existed that could cause valid Rust code to trigger compiler crashes or miscompilations. Raising the baseline addresses these issues and enables more complete support for the remaining supported hardware.
Removing support affects users of the architectures being removed. In this case, the most recent affected GPU architectures date back to 2017 and are no longer actively supported by NVIDIA. “Maintaining support for these older architectures requires substantial effort that detracts from improving modern targets,” the team added. The overall impact of this change is expected to be limited, as most developers have moved to Volta or newer GPUs.
What This Means for Developers
If you need to target a CUDA driver that does not support PTX ISA 7.0 (CUDA 10-era drivers and older), Rust 1.97 will no longer be able to generate PTX compatible with that environment. Similarly, if you need to run on GPUs with compute capability below 7.0 (for example, Maxwell or Pascal), Rust 1.97 will no longer be able to generate compatible PTX for those GPUs.
Assuming you are targeting a CUDA driver compatible with CUDA 11 or newer and using GPUs with compute capability 7.0 or newer, the default behavior changes:
- If you do not specify
-C target-cpu, the new default will besm_70, and your build should continue to work (but will no longer be compatible with pre-Volta GPUs). - If you currently specify an older
-C target-cpu(for example,sm_60), you will need to either remove that flag and let it default tosm_70, or update it tosm_70or a newer architecture.
If you already specify -C target-cpu=sm_70 (or newer), there should be no behavioral changes from this update. For more details on building and configuring nvptx64-nvidia-cuda, see the platform support documentation.
For a deeper understanding of the reasoning behind this change, refer to the Background section above. The Rust compiler team emphasizes that this is a targeted removal to improve stability and focus resources on modern, widely-used hardware.