metal : enable shader debugging (cmake option) (#4705)
* ggml : disable fast-math for Metal (cmake build only) ggml-ci * metal : fix Metal API debug warnings * cmake : add -fno-inline for Metal build (#4545) * metal : fix API debug warnings * metal : fix compile warnings * metal : use uint64_t for strides * cmake : rename option to LLAMA_METAL_SHADER_DEBUG * metal : fix mat-vec Q8_0 kernel for BS > 1 * metal : normalize mat-vec kernel signatures * cmake : respect LLAMA_QKK_64 option * metal : fix mat-vec Q4_K kernel for QK_K == 64 ggml-ci
G
Georgi Gerganov committed
58ba655af054715c0516ee270ad028ad9e74f357
Parent: edd1ab7
Committed by GitHub <noreply@github.com>
on 1/2/2024, 8:57:44 AM