[quantization][DRAFT] Disk space consumption improvements for full model quantization#495
Draft
stamalakhov wants to merge 2 commits intoSamsung:mainfrom
Draft
[quantization][DRAFT] Disk space consumption improvements for full model quantization#495stamalakhov wants to merge 2 commits intoSamsung:mainfrom
stamalakhov wants to merge 2 commits intoSamsung:mainfrom
Conversation
This PR quantizes the full `LLama` model and converts it to circle format. TICO-DCO-1.0-Signed-off-by: s.malakhov <s.malakhov@partner.samsung.com>
This PR fixes population of static `causal_masks`\`position_embeddings` through the layers to save disk space. TICO-DCO-1.0-Signed-off-by: s.malakhov <s.malakhov@partner.samsung.com>
stamalakhov
changed the title
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR fixes population of static
causal_masks`position_embeddings` through the layers to save disk space.It precomputes static
causal_mask/position_embeddingsfor using inllama/quant_decoder_layerto prevent populating every quantized decoder layer with these statically computed parameters to save disk space.Using this PR
circlemodel forHuggingFaceTB/SmolLM2-135M-Instructis just 105MiB (vs 300 Mib of #492)Draft: #436
TICO-DCO-1.0-Signed-off-by: s.malakhov s.malakhov@partner.samsung.com