feat: Introduce K/V Context Quantisation (vRAM improvements) #4422
test.yaml
on: pull_request
generate-windows-rocm
19m 41s
generate-windows-cuda
24m 21s
Matrix: generate-cuda
Matrix: generate-rocm
Matrix: generate
Annotations
3 warnings
|
test (windows-2019, amd64)
No files were found with the provided path: ollama. No artifacts will be uploaded.
|
|
generate-cuda (11.8.0)
The following actions use a deprecated Node.js version and will be forced to run on node20: actions/setup-go@v4. For more info: https://github.blog/changelog/2024-03-07-github-actions-all-actions-will-run-on-node20-instead-of-node16-by-default/
|
|
generate-rocm (6.1.2)
The following actions use a deprecated Node.js version and will be forced to run on node20: actions/setup-go@v4. 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 | |
|---|---|---|
|
cuda-11.8.0-libraries
|
205 MB |
|
|
macos-latest-amd64-libraries
|
9.7 MB |
|
|
macos-latest-arm64-libraries
|
4.09 MB |
|
|
macos-latest-binaries
|
17.5 MB |
|
|
rocm-6.1.2-libraries
|
124 MB |
|
|
ubuntu-latest-amd64-libraries
|
7.5 MB |
|
|
ubuntu-latest-binaries
|
16.2 MB |
|
|
windows-2019-amd64-libraries
|
4.46 MB |
|