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

refactor : remove libcurl, use OpenSSL when available (#18828)

Browse source
This commit is contained in:
Adrien Gallouët 2026-01-14 18:02:47 +01:00 • committed by GitHub
parent 3e4bb29666
commit 516a4ca9b5
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
36 changed files with 74 additions and 500 deletions
Download patch file Download diff file Expand all files Collapse all files

4
examples/sycl/build.sh
View file

@ -8,10 +8,10 @@ cd build
source /opt/intel/oneapi/setvars.sh
#for FP16
#cmake .. -DGGML_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DGGML_SYCL_F16=ON -DLLAMA_CURL=OFF # faster for long-prompt inference
#cmake .. -DGGML_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DGGML_SYCL_F16=ON -DLLAMA_OPENSSL=OFF # faster for long-prompt inference
#for FP32
cmake .. -DGGML_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DLLAMA_CURL=OFF
cmake .. -DGGML_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DLLAMA_OPENSSL=OFF
#build example/main
#cmake --build . --config Release --target main