8000 CUDA: build archs as virtual for GGML_NATIVE=OFF by JohannesGaessler · Pull Request #13135 · ggml-org/llama.cpp · GitHub
[go: up one dir, main page]
Skip to content

CUDA: build archs as virtual for GGML_NATIVE=OFF#13135

Merged
JohannesGaessler merged 1 commit intoggml-org:masterfrom
JohannesGaessler:cuda-jit
May 6, 2025
Merged

CUDA: build archs as virtual for GGML_NATIVE=OFF#13135
JohannesGaessler merged 1 commit intoggml-org:masterfrom
JohannesGaessler:cuda-jit

Commits

Commits on May 6, 2025
0