fix(docs): correct cross-model coefficient count from 4 to 7#479
Merged
sriumcp merged 1 commit intoinference-sim:mainfrom Mar 3, 2026
Merged
fix(docs): correct cross-model coefficient count from 4 to 7#479sriumcp merged 1 commit intoinference-sim:mainfrom
sriumcp merged 1 commit intoinference-sim:mainfrom
Conversation
…+ 3 alpha) The cross-model backend uses 7 globally-fitted coefficients, not 4: - 4 beta coefficients for step time (per-layer, KV bandwidth, MoE dispatch, TP sync) - 3 alpha coefficients for CPU overhead (pre-scheduling, per-token, output processing) All 7 are model-independent and stored in crossmodel_defaults. The "4 coefficients" framing incorrectly excluded the alpha parameters which are equally global. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
The cross-model backend documentation incorrectly states "4 globally-fitted coefficients" when it actually uses 7: 4 beta (step time) + 3 alpha (CPU overhead). All 7 are model-independent and stored in
crossmodel_defaultsindefaults.yaml.Changes
docs/guide/latency-models.md: "4 globally-fitted physics coefficients" → "7 globally-fitted coefficients (4 beta for step time + 3 alpha for CPU overhead)"docs/reference/configuration.md: same fix in mode selection descriptionCLAUDE.md: expanded to list all 7 coefficient rolesContext
The "4 coefficients" framing propagated from the issue design (#472) which focused on the StepTime formula (4 beta terms) and treated the alpha coefficients as a footnote. But from the user's perspective, all 7 come from
crossmodel_defaults— they're all part of the cross-model prediction.🤖 Generated with Claude Code