Skip to content

ggml-cuda: drop the CUDA graph cache count cap, as upstream does - #253

Merged
danielhanchen merged 2 commits into
carry/superseded-pin-optimizationsfrom
fix/cuda-graph-cache-no-cap
Oct 9, 2026
Merged

ggml-cuda: drop the CUDA graph cache count cap, as upstream does#253
danielhanchen merged 2 commits into
carry/superseded-pin-optimizationsfrom
fix/cuda-graph-cache-no-cap

Commits

  1. Commits on Oct 8, 2026