gittensor-ai-lab/sparkinfer: raise maintainer_cut to 0.5#1556
Closed
ai-hpc wants to merge 3 commits into
Closed
Conversation
Allocate more of the subnet emission to the core team to productionize the engine and fund a new AI research engineer joining the project — building momentum toward the production runtime. Contributors still receive the majority (0.5) of the per-PR allocation.
ai-hpc
force-pushed
the
sparkinfer-maintainer-cut-0.6
branch
from
038d2a2 to
7beadc8
Compare
ai-hpc
changed the title
Contributor
Author
|
Superseding this maintainer_cut change with a separate governance PR that sets the sparkinfer credibility threshold (min_credibility 0.4). Closing. |
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Raises
maintainer_cutfor gittensor-ai-lab/sparkinfer from 0.3 → 0.5 ingittensor/validator/weights/master_repositories.json.Why
We are putting more of our subnet emission behind productionizing the engine. sparkinfer just landed the first kernel-level decode win over llama.cpp (v0.3.0 — 388 tok/s on RTX 5090, +4.5%), and we are onboarding a new AI research engineer to carry that momentum into a production runtime: native weight format, thermal-safe inference, and agent-first serving.
A larger maintainer cut funds that core R&D + productionization push, while contributors still receive the majority (0.5) of each PR allocation. The eval gate, label multipliers, and contributor rewards are otherwise unchanged — this only adjusts the maintainer/contributor split of our own repo allocation (
trusted_label_pipeline: true).Single-line change to our entry only; no other repositories affected.