Abstract
Model checkpoints are growing in both number and size, which makes archival, transfer, and deployment increasingly costly. General-purpose compressors can reduce storage requirements but ignore tensor structure, whereas existing tensor-specific compressors rely on fixed and format-specific pipelines. We present Brevis, which formulates lossless tensor compression as program synthesis. We design a typed domain-specific language (DSL) that captures recurring tensor structures, such as repeated regions and floating-point fields, through a set of reversible operators. Given a tensor, Brevis synthesizes a self-contained DSL program that reconstructs it bit-exactly. A checkpoint-specific production prior, learned from a small representative sample of tensors, guides a bounded A* search to synthesize compact programs, which can later be executed directly for bit-exact decompression. On 10 public checkpoints spanning language, audio, and image generation models, Brevis reduces 2.13 TB of checkpoint data to 1.41 TB, a 33.93% storage reduction. It produces archives up to 30.87% smaller than those of four general-purpose compressors, including zstd and gzip, and smaller archives than the tensor-specific compressors ZipNN and DFloat11. Under a practical concurrency configuration, Brevis achieves 3.60 GB/s compression and 6.61 GB/s decompression while preserving every source byte.
Community
Brevis formulates lossless tensor compression as program synthesis, generating compact, executable DSL programs that achieve superior storage reduction and high-speed, bit-exact reconstruction for large model checkpoints.
Paper: https://arxiv.org/abs/2608.02162
Code: https://github.com/jiekeshi/Brevis
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- Approaching Shannon Bound with Lossless LLM Weight Compression (2026)
- LLM-based Source Code Compression via Thresholded Symbol Ranking (2026)
- Xema: Efficient Diffusion Serving through Fine-Grained Memory Management and Auto-Configuration (2026)
- EVOLVE: Efficient Learned Volume Compression with Variable-Rate Encoding on a Cross-Domain Database (2026)
- SharQ: Bridging Activation Sparsity and FP4 Quantization for LLM Inference (2026)
- Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference (2026)
- FSZ: Breaking the Prediction-Throughput Trade-off in GPU Lossy Compression (2026)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend
Get this paper in your agent:
hf papers read 2608.02162 Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper