Sparse-attention models will not run on Ampere GPUs
DeepSeek V4 and sparse-MLA models fail on Ampere sm_80 GPUs such as A100 and A800 with unsupported architecture errors.
Tier II · Emerging Problems that are still building up.
3 public reports · first reported 24 March 2026 · last reported 31 July 2026
What's going wrong
Users with A100, A800 and other Ampere cards cannot start newer DeepSeek sparse-attention models.
AI-assisted: written with the help of AI from the reports. The idea report has the full summary.
In the idea report
- The full summary.
- The products the 3 reports are about, and how many came each month.
- Related problems.
No business has been found with this problem yet, so the report has no contacts. All sales are final — no refunds. Pricing.