github ggml-org/llama.cpp b7538
on GitHub

latest releases: b7540, b7539
8 hours ago
Details

ggml-cuda: fix blackwell native builds (#18361)

  • ggml-cuda: fix blackwell native builds

Replace 12x in native architectures by 12xa

  • replace for GGML_NATIVE=OFF too

  • only replace for native

  • remove 120f-virtual for default compilation

Co-authored-by: Aman Gupta

macOS/iOS:

Linux:

Windows:

openEuler:

Check out latest releases or
releases around ggml-org/llama.cpp b7538

Don't miss a new llama.cpp release

NewReleases is sending notifications on new releases.

Get notifications