bench-server-baseline (phi-2, q4_0)
Details
Push Docker image to Docker Hub (light, .devops/main.Dockerfile, linux/amd64,linux/arm64)
Details
bench-server-baseline (phi-2, q8_0)
Details
Push Docker image to Docker Hub (full, .devops/full.Dockerfile, linux/amd64,linux/arm64)
Details
bench-server-baseline (phi-2, f16)
Details
Push Docker image to Docker Hub (server, .devops/server.Dockerfile, linux/amd64,linux/arm64)
Details
Push Docker image to Docker Hub (light-cuda, .devops/main-cuda.Dockerfile, linux/amd64)
Details
Push Docker image to Docker Hub (full-cuda, .devops/full-cuda.Dockerfile, linux/amd64)
Details
Push Docker image to Docker Hub (server-cuda, .devops/server-cuda.Dockerfile, linux/amd64)
Details
Push Docker image to Docker Hub (light-rocm, .devops/main-rocm.Dockerfile, linux/amd64,linux/arm64)
Details
Push Docker image to Docker Hub (full-rocm, .devops/full-rocm.Dockerfile, linux/amd64,linux/arm64)
Details
Push Docker image to Docker Hub (server-rocm, .devops/server-rocm.Dockerfile, linux/amd64,linux/a...
Details
Push Docker image to Docker Hub (light-intel, .devops/main-intel.Dockerfile, linux/amd64)
Details
Push Docker image to Docker Hub (server-intel, .devops/server-intel.Dockerfile, linux/amd64)
Details
ubuntu-latest-cmake-mpi (mpich)
Details
ubuntu-latest-cmake-mpi (libopenmpi-dev)
Details
macOS-latest-swift (generic/platform=macOS)
Details
macOS-latest-swift (generic/platform=iOS)
Details
macOS-latest-swift (generic/platform=tvOS)
Details
windows-latest-cmake (noavx, -DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX=OFF -DLLAMA_A...
Details
windows-latest-cmake (avx2, -DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DBUILD_SHARED_LIBS=ON)
Details
windows-latest-cmake (avx, -DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX2=OFF -DBUILD_SH...
Details
windows-latest-cmake (avx512, -DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX512=ON -DBUIL...
Details
windows-latest-cmake (clblast, -DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_CLBLAST=ON -DBU...
Details
windows-latest-cmake (openblas, -DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_BLAS=ON -DBUIL...
Details
windows-latest-cmake (kompute, -DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_KOMPUTE=ON -DKO...
Details
windows-latest-cmake (vulkan, -DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_VULKAN=ON -DBUIL...
Details
windows-latest-cmake (arm64, -A ARM64 -DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DBUILD_SHARED_L...
Details
windows-latest-cmake-cuda (12.2.0, cuda)
Details
windows-latest-cmake-cuda (11.7.1, cuda)
Details
bench-server-bench-server-baseline-Standard_NC4as_T4_v3-phi-2-f16
{"i":391,"req":{"p95":31385.18,"avg":11934.72},"pp":{"p95":809.05,"avg":152.96,"0":768.83},"tg":{"p95":24.14,"avg":18.87,"0":18.42}}
Details
bench-server-bench-server-baseline-Standard_NC4as_T4_v3-phi-2-q4_0
{"i":462,"req":{"p95":27753.38,"avg":10248.29},"pp":{"p95":512.58,"avg":113.07,"0":606.49},"tg":{"p95":36.95,"avg":23.87,"0":22.3}}
Details
bench-server-bench-server-baseline-Standard_NC4as_T4_v3-phi-2-q8_0
{"i":408,"req":{"p95":27869.64,"avg":11558.1},"pp":{"p95":557.83,"avg":130.42,"0":669.54},"tg":{"p95":31.64,"avg":25.94,"0":21.07}}
Details