WIP Proposal: Multi-spec Models#468
Open
nstogner wants to merge 3 commits into
Open
Conversation
samos123
reviewed
Mar 24, 2025
| # indicates that this spec should be scaled with the previous one. | ||
| # TBD: Not sure on the field name yet, this should likely be a followup-feature, not a part | ||
| # of the initial implementation. | ||
| simultaneousScaleUpGroup: foo |
Contributor
There was a problem hiding this comment.
I probably prefer this as a scaleUpStrategy block on the main model spec:
spec:
scaleUp:
strategy: fanout
groups: # ordered list of groups
- gpu-l4-70b, tpu-v5e-8b
- cpu-3b
^^ means it would first try fanout for gpu-l4-70b, tpu-v5e-8b, trying to scale up both l4 and v5e at the same time. If both fail then it would try to scale up cpu-3b
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Support heterogenous scaling & routing.
Also see issues: #428