[sharktank] make fp4 block-quantized have scales with trailing singleton dimension #7057
sogartarci-llama-quick-tests.yaml
on: pull_request
Matrix: Llama Benchmarking 8B Tests
Annotations
1 warning
|
Llama Benchmarking 8B Tests (3.11)
The `set-output` command is deprecated and will be disabled soon. Please upgrade to using Environment Files. For more information see: https://github.blog/changelog/2022-10-11-github-actions-deprecating-save-state-and-set-output-commands/
|
Artifacts
Produced during runtime
| Name | Size | Digest | |
|---|---|---|---|
|
llama-files
|
529 KB |
sha256:034fa4cedf124cbddb6cb2a681d6060ce581801121aae9828fb32a8235d374da
|
|