[PR #11913] Revert "cuda: leverage JIT for smaller footprint (#11635)" #13655

Closed
opened 2026-04-13 00:32:06 -05:00 by GiteaMirror · 0 comments
Owner

Original Pull Request: https://github.com/ollama/ollama/pull/11913

State: closed
Merged: Yes


This reverts commit dc5a645434.

Looks like this is causing problems on some systems. I'll investigate deeper later to see if there's some way to re-enable the savings, but for now, back this out to get a good build.

CUDA error: the provided PTX was compiled with an unsupported toolchain.
  current device: 0, in function ggml_cuda_mul_mat_q at //ml/backend/ggml/ggml/src/ggml-cuda/mmq.cu:129
  cudaGetLastError()
**Original Pull Request:** https://github.com/ollama/ollama/pull/11913 **State:** closed **Merged:** Yes --- This reverts commit dc5a645434f0ea6364c426c6ba112da1afa40cb2. Looks like this is causing problems on some systems. I'll investigate deeper later to see if there's some way to re-enable the savings, but for now, back this out to get a good build. ``` CUDA error: the provided PTX was compiled with an unsupported toolchain. current device: 0, in function ggml_cuda_mul_mat_q at //ml/backend/ggml/ggml/src/ggml-cuda/mmq.cu:129 cudaGetLastError() ```
GiteaMirror added the pull-request label 2026-04-13 00:32:06 -05:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#13655