docs: add HIP/AMD NaN warning for q8_0/turbo3 on large K-norm models#66
Open
brosequist wants to merge 1 commit intoTheTom:mainfrom
Open
docs: add HIP/AMD NaN warning for q8_0/turbo3 on large K-norm models#66brosequist wants to merge 1 commit intoTheTom:mainfrom
brosequist wants to merge 1 commit intoTheTom:mainfrom
Conversation
Adds a prominent WARNING block to turboquant-recommendations.md documenting the observed NaN divergence when using q8_0 or turbo3 compression on models with large K-vector norms (e.g. Qwen2.5-7B) on AMD/ROCm (HIP) backends. The root cause is the int8 overflow path that differs between HIP and CUDA. Recommended mitigations: switch to turbo2/turbo4 or add pre-quantization K-norm clipping. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
docs/turboquant-recommendations.mddocumenting observed NaN divergence when usingq8_0orturbo3on models with large K-vector norms (e.g. Qwen2.5-7B) on AMD/ROCm (HIP) backends.Test plan
🤖 Generated with Claude Code