fix(hub): pull the backend-native CUDA bundle, not the universal quant - #38
Merged
Conversation
basert pull <id> on a CUDA host resolved cuda-q4mix correctly but cmd_pull
gated on quant_tag(variant)==want ("q4mix"!="q4") and fell back to the
universal f16-scale default-q4, which CUDA can't load (no 'gemv_q4'). Match on
quant bits (like installed_best_variant / the resolver). Verified on GB10.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
basert pull/chat <id>on NVIDIA GB10 downloaded the universal f16-scaledefault-q4(unloadable on CUDA —no function named 'gemv_q4') instead of the resolvedcuda-q4mix. cmd_pull gated on a rawquant_tag(variant)==want("q4mix"!="q4"); now matches on quant bits like the resolver /installed_best_variant. Verified on GB10: pullscuda-q4mix.baseand loads. Mirrors internal fix.