Skip to content
Publish Docker image

llama : only use default buffer types for the KV cache (#10358) #14726

Sign in to view logs

llama : only use default buffer types for the KV cache (#10358)

llama : only use default buffer types for the KV cache (#10358) #14726

Triggered via push November 17, 2024 11:25
@slarenslaren
pushed be5cacc
master
Status Failure
Total duration 24m 59s
Artifacts 1

docker.yml

on: push
Matrix: Push Docker image to Docker Hub
Fit to window
Zoom out
Zoom in

Annotations

12 errors and 1 warning
Push Docker image to Docker Hub (light-intel, .devops/llama-cli-intel.Dockerfile, linux/amd64)
The job was canceled because "full-cuda__devops_full-cu" failed.
Push Docker image to Docker Hub (full-cuda, .devops/full-cuda.Dockerfile, linux/amd64)
buildx failed with: ERROR: failed to solve: process "/bin/sh -c if [ \"${CUDA_DOCKER_ARCH}\" != \"default\" ]; then export CMAKE_ARGS=\"-DCMAKE_CUDA_ARCHITECTURES=${CUDA_DOCKER_ARCH}\"; fi && cmake -B build -DGGML_CUDA=ON -DLLAMA_CURL=ON ${CMAKE_ARGS} -DCMAKE_EXE_LINKER_FLAGS=-Wl,--allow-shlib-undefined . && cmake --build build --config Release -j$(nproc) && cp build/bin/* ." did not complete successfully: exit code: 1
Push Docker image to Docker Hub (server-intel, .devops/llama-server-intel.Dockerfile, linux/amd64)
The job was canceled because "full-cuda__devops_full-cu" failed.
Push Docker image to Docker Hub (server, .devops/llama-server.Dockerfile, linux/amd64,linux/arm64)
The job was canceled because "full-cuda__devops_full-cu" failed.
Push Docker image to Docker Hub (server-cuda, .devops/llama-server-cuda.Dockerfile, linux/amd64)
The job was canceled because "full-cuda__devops_full-cu" failed.
Push Docker image to Docker Hub (light-musa, .devops/llama-cli-musa.Dockerfile, linux/amd64)
The job was canceled because "full-cuda__devops_full-cu" failed.
Push Docker image to Docker Hub (server-musa, .devops/llama-server-musa.Dockerfile, linux/amd64)
The job was canceled because "full-cuda__devops_full-cu" failed.
Push Docker image to Docker Hub (full-musa, .devops/full-musa.Dockerfile, linux/amd64)
The job was canceled because "full-cuda__devops_full-cu" failed.
Push Docker image to Docker Hub (full, .devops/full.Dockerfile, linux/amd64,linux/arm64)
The job was canceled because "full-cuda__devops_full-cu" failed.
Push Docker image to Docker Hub (full, .devops/full.Dockerfile, linux/amd64,linux/arm64)
The operation was canceled.
Push Docker image to Docker Hub (light-cuda, .devops/llama-cli-cuda.Dockerfile, linux/amd64)
The job was canceled because "full-cuda__devops_full-cu" failed.
Push Docker image to Docker Hub (light, .devops/llama-cli.Dockerfile, linux/amd64,linux/arm64)
The job was canceled because "full-cuda__devops_full-cu" failed.
Push Docker image to Docker Hub (full-cuda, .devops/full-cuda.Dockerfile, linux/amd64)
The following actions use a deprecated Node.js version and will be forced to run on node20: docker/setup-qemu-action@v2, docker/setup-buildx-action@v2, docker/login-action@v2. For more info: https://github.blog/changelog/2024-03-07-github-actions-all-actions-will-run-on-node20-instead-of-node16-by-default/

Artifacts

Produced during runtime
Name Size
ggerganov~llama.cpp~BQ7GQ0.dockerbuild
39.1 KB