thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4

llama : allow using iGPUs with --device (#15951)

Browse source 
* llama : allow using iGPUs with --device

* mtmd : allow iGPU

* rpc-server : allow iGPU
This commit is contained in:
Diego Devesa 2025-09-13 07:49:49 -07:00 • committed by GitHub
parent 55758b00ca
commit 50f4281a6f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 8 additions and 24 deletions
Download patch file Download diff file Expand all files Collapse all files

1
tools/mtmd/clip.cpp
View file

@ -406,6 +406,7 @@ struct clip_ctx {
}
if (!backend) {
backend = ggml_backend_init_by_type(GGML_BACKEND_DEVICE_TYPE_GPU, nullptr);
backend = backend ? backend : ggml_backend_init_by_type(GGML_BACKEND_DEVICE_TYPE_IGPU, nullptr);
}
}