replica
/
llama.cpp
mirror of https://github.com/ggml-org/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
1,040 Commits 472 Branches 4,051 Tags 562 MiB
Commit Graph

2 Commits

Author SHA1 Message Date
Shouzheng Liu fc8ef549e5
metal : enable ggml-alloc (#2627) 
* metal: enable ggml-alloc

Make ggml-alloc work with concurrently dispatch.

* style-fix

Co-authored-by: slaren <slarengh@gmail.com>

---------

Co-authored-by: slaren <slarengh@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
 2023-08-16 23:08:28 +03:00
slaren a113689571
ggml : add graph tensor allocator (#2411) 
* ggml : add graph tensor allocator

* ggml : don't calculate data pointer of unallocated tensors when creating a view with an offset

* ggml : refactor ggml_view_Nd into ggml_view_tensor_offset
 2023-07-30 15:58:01 +02:00