[quantization][draft] [NO_MERGE] Fix instability#670
Draft
stamalakhov wants to merge 1 commit into
Draft
Conversation
6cb7426 to
f883c88
Compare
This PR tries to fix instability in llama quantization. TICO-DCO-1.0-Signed-off-by: s.malakhov <s.malakhov@partner.samsung.com>
f883c88 to
07189f8
Compare
This was referenced May 13, 2026
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR tries to fix instability in llama quantization.
results of ppl evaluation for
LLama3.2-3B-Instructquantized using GPTQ only (smse) on 128 samplestorch and transformers packages were the same on all GPUs:
with
gptq_use_orig_modelenabled:Relative error:
Related: #656
TICO-DCO-1.0-Signed-off-by: s.malakhov s.malakhov@partner.samsung.com