happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

metal: use shared buffers on eGPU (#17866) 

* metal: use shared buffers on eGPU

With #15906, I noticed on important regression when using metal backend on eGPU.
This commit restore the previous behavior and add an option to force its activation.

* metal: use shared buffers on eGPU

* metal: use shared buffers on eGPU
This commit is contained in:
Jeremy Demeule 2025-12-15 15:14:49 +01:00 committed by GitHub
parent 96a181a933
commit 165caaf5fb
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 7 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
ggml/src/ggml-metal/ggml-metal-device.m
View File

@ -769,9 +769,16 @@ ggml_metal_device_t ggml_metal_device_init(void) {
#endif
dev->props.use_shared_buffers = dev->props.has_unified_memory;
#if TARGET_OS_OSX
// In case of eGPU, shared memory may be preferable.
dev->props.use_shared_buffers |= [dev->mtl_device location] == MTLDeviceLocationExternal;
#endif
if (getenv("GGML_METAL_SHARED_BUFFERS_DISABLE") != NULL) {
dev->props.use_shared_buffers = false;
}
if (getenv("GGML_METAL_SHARED_BUFFERS_ENABLE") != NULL) {
dev->props.use_shared_buffers = true;
}
dev->props.supports_gpu_family_apple7 = [dev->mtl_device supportsFamily:MTLGPUFamilyApple7];