fix: V-norm in memory_stats, SeedSequence PRNG, streaming API, serialization#61
Open
brosequist wants to merge 1 commit intoTheTom:mainfrom
Open
fix: V-norm in memory_stats, SeedSequence PRNG, streaming API, serialization#61brosequist wants to merge 1 commit intoTheTom:mainfrom
brosequist wants to merge 1 commit intoTheTom:mainfrom
Conversation
…essed_size_bits KVCacheCompressor.memory_stats() omitted the float32 norm stored per V vector, inflating the reported compression ratio. Add v_bits_total += n_vectors * 32 to account for it. Also adds compressed_size_bits() to TurboQuantMSE (was missing; TurboQuant already had it), fixing the asymmetry between the two classes. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Owner
|
hey there. thank you for the contribution. i'll be getting to them. I apologize for the delay. |
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
KVCacheCompressor.memory_stats()omitted the 32-bit float norm stored per V vector, inflating the reported compression ratio. Addsv_bits_total += n_vectors * 32.compressed_size_bits()toTurboQuantMSE(was missing;TurboQuantalready had it).seed + 1000offset withnp.random.SeedSequence(seed).spawn(2)for true PRNG independence between the PolarQuant and QJL stages.compress_token()/get_compressed_cache()streaming API toKVCacheCompressorfor auto-regressive token-by-token inference.CompressedVector.to_bytes()/from_bytes()for disk/network serialization.Test plan
pytest tests/test_kv_cache.pycovers all new paths including memory_stats accuracy, streaming API, and serialization round-trip.🤖 Generated with Claude Code