Skip to content

LLM inference in C/C++

C++ ggml

Enable OpenSSL in FP32/FP16 SYCL builds to restore HF HTTPS downloads (#30330)

Raffaele Di Donna091b6a7fc561
diff --git a/docs/backend/SYCL.md b/docs/backend/SYCL.md
index 19dc698514..32a209a262 100644
--- a/docs/backend/SYCL.md
+++ b/docs/backend/SYCL.md
@@ -313,6 +313,8 @@ When targeting an intel GPU, the user should expect one or more devices among th
### II. Build llama.cpp
+HTTPS downloads, including Hugging Face models, require OpenSSL development libraries at build time. See the [build prerequisites](../build.md) for installation commands. If OpenSSL is not found, the build can still complete without HTTPS support.
+
#### Intel GPU
```sh
diff --git a/examples/sycl/build.sh b/examples/sycl/build.sh
index 9dd66cb676..bec96886b1 100755
--- a/examples/sycl/build.sh
+++ b/examples/sycl/build.sh
@@ -37,10 +37,10 @@ source /opt/intel/oneapi/setvars.sh
if [ "$PRECISION" = "fp16" ]; then
#for FP16
- cmake .. -DGGML_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DGGML_SYCL_F16=ON -DLLAMA_OPENSSL=OFF # faster for long-prompt inference
+ cmake .. -DGGML_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DGGML_SYCL_F16=ON -DLLAMA_OPENSSL=ON # faster for long-prompt inference
else
#for FP32
- cmake .. -DGGML_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DLLAMA_OPENSSL=OFF
+ cmake .. -DGGML_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DLLAMA_OPENSSL=ON
fi
#build example/main