diff --git a/backend/cpp/turboquant/Makefile b/backend/cpp/turboquant/Makefile index 9a70bb1b5..27a113796 100644 --- a/backend/cpp/turboquant/Makefile +++ b/backend/cpp/turboquant/Makefile @@ -1,7 +1,7 @@ # Pinned to the HEAD of feature/turboquant-kv-cache on https://github.com/TheTom/llama-cpp-turboquant. # Auto-bumped nightly by .github/workflows/bump_deps.yaml. -TURBOQUANT_VERSION?=8a891f4b566efdbd3cea92fafee3227a0a267683 +TURBOQUANT_VERSION?=407f3237bfb3eeaff61546797de3d8c1a96be748 LLAMA_REPO?=https://github.com/TheTom/llama-cpp-turboquant CMAKE_ARGS?= @@ -101,10 +101,10 @@ turboquant-cpu-all: @echo "Collected ggml shared backends:" && ls -la ggml-shared-libs/ turboquant-grpc: - $(call turboquant-build,grpc,-DGGML_RPC=ON -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off,--target grpc-server --target rpc-server) + $(call turboquant-build,grpc,-DGGML_RPC=ON -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off,--target grpc-server --target ggml-rpc-server) turboquant-rpc-server: turboquant-grpc - cp -rf $(CURRENT_MAKEFILE_DIR)/../turboquant-grpc-build/llama.cpp/build/bin/rpc-server turboquant-rpc-server + cp -rf $(CURRENT_MAKEFILE_DIR)/../turboquant-grpc-build/llama.cpp/build/bin/ggml-rpc-server turboquant-rpc-server package: bash package.sh