Support file paths for ONNX predictor #1711
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Conflicts: # docs/workloads/realtime/configuration.md
…paths # Conflicts: # pkg/types/spec/errors.go # pkg/types/spec/validations.go
…paths # Conflicts: # cli/local/model_cache.go # pkg/types/spec/validations.go # pkg/workloads/cortex/lib/model/type.py
RobertLucian
changed the base branch from
master
to
improvement/python-api-spec
deliahu
reviewed
Dec 20, 2020
pkg/operator/operator/k8s.go
Outdated
| if api.Predictor.Models.Path != nil && strings.HasSuffix(*api.Predictor.Models.Path, ".onnx") { | ||
| downloadContainerArs = append(downloadContainerArs, downloadContainerArg{ | ||
| From: *api.Predictor.Models.Path, | ||
| To: path.Join(_modelDir, consts.SingleModelName, "1"), |
There was a problem hiding this comment.
nit: I think if we add ItemName: "the onnx model" to the struct, it will print a nice message in the downloader container
There was a problem hiding this comment.
Thought of not doing it because adding this log would have been misleading since we advertise the predictor.models predictor as having the LR active. That being said, I actually think this is a good idea because it highlights to the user that a model gets downloaded at deploy time (suggestive that it's a special case and LR is not active) and it's also potentially easier for us to debug if the user shares their logs.
# Conflicts: # cli/local/docker_spec.go # cli/local/model_cache.go # docs/workloads/batch/configuration.md # docs/workloads/realtime/configuration.md # docs/workloads/realtime/models.md # docs/workloads/realtime/predictors.md # pkg/cortex/serve/cortex_internal/lib/model/type.py # pkg/operator/operator/k8s.go # pkg/types/spec/errors.go # pkg/types/spec/validations.go # pkg/types/userconfig/api.go
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Closes #1686.
Blocked on #1702.
checklist:
make testandmake lint