mirror of
https://github.com/likelovewant/ollama-for-amd.git
synced 2025-12-21 22:33:56 +00:00
0cf7794b16
* Revert "vulkan: temporary cary of vulkan fixes (#12971)"
This reverts commit 3a9e8e9fd4.
* ggml update to b7087
* fix argsort on metal
* update to b7108
* fix bakllava regression
This model lacks the metadata for the projector type.
* update to b7209
* fix TopK perf
* only build arm code on arm
5 lines
169 B
C++
Vendored
Generated
5 lines
169 B
C++
Vendored
Generated
int LLAMA_BUILD_NUMBER = 0;
|
|
char const *LLAMA_COMMIT = "7f8ef50cce40e3e7e4526a3696cb45658190e69a";
|
|
char const *LLAMA_COMPILER = "";
|
|
char const *LLAMA_BUILD_TARGET = "";
|