mirror of
https://github.com/deepseek-ai/DeepGEMM.git
synced 2026-11-05 00:47:26 +00:00
[GH-ISSUE #216] Question: planned support for Geforce GPUs (at least Blackwell sm_12x).. #126
Labels
No labels
pull-request
No milestone
No project
No assignees
1 participant
Notifications
Due date
No due date set.
Dependencies
No dependencies set.
Reference
deepseek-ai/DeepGEMM#126
Loading…
Add table
Add a link
Reference in a new issue
No description provided.
Delete branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Originally created by @oscarbg on GitHub (Oct 15, 2025).
Original GitHub issue: https://github.com/deepseek-ai/DeepGEMM/issues/216
Hi,
altough Geforce Ada (sm_89) also has fp8 tensor core support and fp8 it's supported on cutlass since very recently tough (4.0 or 4.1 I think)..
thanks..
@LyricZhao commented on GitHub (Dec 5, 2025):
Sorry, as we don't have SM89/120 devices, we don't have plans or people to support this. From my perspective, adding a new architecture support is hard for us to maintain, e.g. the GEMM heuristics are hard to cover all archs. So we encourage the OSS community makes a fork and supports it. The main repo is always using the computation center GPUs.