Rename part three#2124
Conversation
Signed-off-by: Shmuel Kallner <kallner@il.ibm.com>
Signed-off-by: Shmuel Kallner <kallner@il.ibm.com>
k8s-ci-robot
added
the
kind/cleanup
✅ Deploy Preview for gateway-api-inference-extension ready!
To edit notification comments on pull requests, go to your Netlify project configuration. |
k8s-ci-robot
added
the
cncf-cla: yes
k8s-ci-robot
added
the
size/L
| func NewMetricsState() *MetricsState { | ||
| return datalayer.NewMetrics() | ||
| } | ||
|
|
There was a problem hiding this comment.
do we still need the MetricsState type defined below?
There was a problem hiding this comment.
Fundamentally no.
I left it in because I didn't want to make the PR larger by updating the old backend metrics scraping code more than absolutely necessary, as the new DataLayer is suppose to replace it.
There was a problem hiding this comment.
ok, so we still have more refactoring to do to get rid of it, I assume that is the end goal, right?
|
/lgtm |
k8s-ci-robot
added
the
lgtm
|
[APPROVALNOTIFIER] This PR is APPROVED This pull-request has been approved by: ahg-g, shmuelk The full list of commands accepted by this bot can be found here. The pull request process is described here DetailsNeeds approval from an approver in each of these files:
Approvers can indicate their approval by writing |
k8s-ci-robot
added
the
approved
|
/test pull-gateway-api-inference-extension-test-unit-main |
|
/test pull-gateway-api-inference-extension-test-e2e-main |
* Removed constructor that used aliased field Signed-off-by: Shmuel Kallner <kallner@il.ibm.com> * Removed references to aliased field Signed-off-by: Shmuel Kallner <kallner@il.ibm.com> --------- Signed-off-by: Shmuel Kallner <kallner@il.ibm.com>
* Removed constructor that used aliased field Signed-off-by: Shmuel Kallner <kallner@il.ibm.com> * Removed references to aliased field Signed-off-by: Shmuel Kallner <kallner@il.ibm.com> --------- Signed-off-by: Shmuel Kallner <kallner@il.ibm.com>
3 participants
What type of PR is this?
/kind cleanup
What this PR does / why we need it:
This PR is a third PR in a set of PRs that is attempting to cleanup the code base WRT to Pods vs Model Server Endpoints and the old "backendmetrics" and the new DataLayer..
It does this by reducing the references to the struct pkg/epp/metrics/MetricsState and instead reference the aliased struct pkg/epp/datalayer/Metrics.
As Model Servers evolve, vLLM or others, one can not assume that there is a one to one relationship between pods and Model Servers. That is a pod may contain multiple Model Servers each. on its own port, such as vLLM's Data Parallel support. On the other hand Model Servers may do there own internal multi-pod routing as well.
Does this PR introduce a user-facing change?: