[WIP][feat] support quantization in delta embedding dump - #629
Open
eric-gecheng wants to merge 1 commit into
Open
[WIP][feat] support quantization in delta embedding dump#629eric-gecheng wants to merge 1 commit into
eric-gecheng wants to merge 1 commit into
Conversation
Add quant_type field to DeltaEmbeddingDumpConfig that enables QUint8RowwiseF16 rowwise quantization (uint8 values + fp16 scale/offset, same format as distributed sparse export) for delta dump parquet output and FeatureStore upload. When INT8 is selected, embeddings are quantized via the existing distributed_quantize_embeddings utility before being written to parquet or submitted to the uploader. The uploader requires no changes — it is already type-agnostic and receives emb_dim+4 as the expected list length to account for the per-row scale/offset trailer.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Add quant_type field to DeltaEmbeddingDumpConfig that enables QUint8RowwiseF16 rowwise quantization (uint8 values + fp16 scale/offset, same format as distributed sparse export) for delta dump parquet output and FeatureStore upload. When INT8 is selected, embeddings are quantized via the existing distributed_quantize_embeddings utility before being written to parquet or submitted to the uploader. The uploader requires no changes — it is already type-agnostic and receives emb_dim+4 as the expected list length to account for the per-row scale/offset trailer.