Commit Graph

2 Commits (2bdc09646d8c6cb74a6f573e9081586b4b83b9d1)

Author SHA1 Message Date
slaren b925f1f1b0
cuBLAS: fall back to pageable memory if pinned alloc fails (#1233)
* cuBLAS: fall back to pageable memory if pinned alloc fails

* cuBLAS: do not use pinned memory if env variable GGML_CUDA_NO_PINNED is set
1 year ago
Georgi Gerganov 84ca9c2ecf
examples : fix save-load-state + rename llama-util.h 1 year ago