Commit graph

3 commits

Author SHA1 Message Date
xloem
ea3a0ad6b6
llama : update stubs for systems without mmap and mlock (#1266)
Co-authored-by: John Doe <john.doe@example.com>
2023-05-01 15:58:51 +03:00
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
2023-05-01 13:32:22 +02:00
Georgi Gerganov
84ca9c2ecf
examples : fix save-load-state + rename llama-util.h 2023-04-29 13:48:11 +03:00
Renamed from llama_util.h (Browse further)