th#964: family lane policy twin — bare conv-UNet bindings AUTO-pick scale-free #fp8 locally#361
Merged
Merged
Conversation
…ngs AUTO-pick scale-free #fp8 locally gen_worker.models.ladder gains family_root (modelfamily.Root twin) and the conv-UNet w8a8 exclusion table; a maybe_rebind_family_fp8 fold (hub-parity AUTO pick over the resolve's sibling_flavors, sm_89+ only, bf16 stays the sub-floor default; pins untouched) runs in the local CLI resolve ahead of the GGUF fold over one shared resolve. WorkerResolvedRepo carries the resolve's model_family (slot-declared family as fallback); select_gguf no longer lets an AUTO-ineligible w8a8 row suppress the GGUF pick. Shared vectors: none in this repo; no format change.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Local-parity half of th#964 (hub commits bb6b8808 / 47bb4bbf): cozy-local ladder picks must match hub picks for conv-UNet families.
gen_worker.models.ladder:family_root(twin of tensorhubmodelfamily.Root),CONV_UNET_W8A8_EXCLUDED_ROOTS= {sd1, sd2, sdxl},w8a8_excluded_for_family, andpick_family_fp8_flavor/maybe_rebind_family_fp8— on sm_89+ a bare excluded-family binding AUTO-picks the best scale-free #fp8 sibling (hub tiebreak, fit-gated); below sm_89 bf16 stays the sub-floor default; explicit pins untouched.WorkerResolvedRepocarries the resolve'smodel_family("" on hubs not sending it — policy off, matching Go's zero-value FamilyRoot); slot-declared family is the fallback, mirroring the hub's binding.Family fallback.resolve_bindings) runs the family fold ahead of the GGUF fold over ONE shared resolve;select_ggufno longer lets an AUTO-ineligible w8a8 row suppress the GGUF pick.Gates: ruff + mypy clean on touched files; full suite 453 passed, 5 skipped, 1 xfailed.
🤖 Generated with Claude Code