arXiv:2608.30384v1 Announce Type: new Abstract: By introducing RSLM (Rotated Scaled Lloyd-Max), a family of training-free vector quantization codecs compressing embeddings to 1--4 bits per dimension,...
arXiv:2605.11608v2 Announce Type: replace-cross Abstract: A single base LLM now comes with dozens of post-training variants, quantized, LoRA-adapted, or distilled, and each has to be checked before r...
arXiv:2607. 18187v1 Announce Type: cross Abstract: Large-scale scientific simulations generate volumetric data at rates that far outpace advances in storage and network bandwidth, making effective lossy compression increasingly critical.
Long-context large language models (LLMs) are increasingly deployed in real-world applications, yet self-attention remains a major efficiency bottleneck -- especially during decoding -- due to the necessity of repeatedly processing ever-growing key-value (KV) caches. Existing sparse attention reduce computation by attending to fewer KV pairs, but often suffer from substantial accuracy degradation, require additional training, or rely on expensive hashing.
arXiv:2608. 04405v1 Announce Type: cross Abstract: Long-context large language models (LLMs) are increasingly deployed in real-world applications, yet self-attention remains a major efficiency bottleneck -- especially during decoding -- due to the necessity of repeatedly processing ever-growing key-value (KV) caches.
The paper introduces D-Quant, a KV cache quantization framework that addresses the memory bottleneck of large language models by using a drift mechanism to convert entropy-coded representations into fixed-size bitstreams. This approach leverages the non-uniform distribution of KV cache values—after rotation and normalization, they approximate a normal distribution—allowing entropy coding to assign shorter codewords to frequent symbols while maintaining regular memory layouts suitable for parallel attention kernels. D-Quant thus aims to reduce memory footprint and bandwidth usage without sacrificing performance.
The quadratic growth of attention computation and key-value (KV) cache with respect to sequence length is a central bottleneck for ultra-long-context language models and high-resolution generative mod...
arXiv:2609.38477v1 Announce Type: cross Abstract: Large language models (LLMs) incur substantial storage, memory-bandwidth and energy costs, motivating compact weight representations. Existing seed-b...
The study evaluates 4‑bit quantization and low‑rank adapter fine‑tuning (QLoRA) on several large protein language models, finding that many model‑task pairs retain over 90% of full fine‑tuning performance while achieving up to 90% GPU memory savings. QLoRA preserves early‑layer representations and induces task‑specific changes in later layers, closely resembling full fine‑tuning with smaller representational shifts. For generative models, 4‑bit quantization largely maintains structural and sequence‑level properties, though token‑level analysis reveals model‑dependent changes in autoregressive output distributions.
arXiv:2510. 00566v4 Announce Type: replace-cross Abstract: Approximate Nearest-Neighbor Search (ANNS) pipelines for high-dimensional neural embeddings spend the bulk of their query time in candidate verification, making it the primary bottleneck in the search process.
arXiv:2510. 04127v2 Announce Type: replace-cross Abstract: Approximate nearest neighbour (ANN) search underpins large-scale retrieval, increasingly within the retrieval-augmented generation pipelines that ground large language models, yet the methods that address it have multiplied across communities until they are seldom read as a single field.
The paper argues that relying solely on zero‑shot task accuracy is insufficient for evaluating quantized large language models (LLMs) because accuracy ignores changes in the full predictive distribution. It proposes a distribution‑sensitive framework that measures fidelity loss by computing statistical distances—such as Jensen‑Shannon Divergence and Total Variation Distance—between the full‑vocabulary output distributions of a full‑precision BF16 reference and its quantized counterparts. Experiments across five foundation architectures and four reasoning benchmarks show that these divergence metrics increase with stronger quantization, revealing distributional drift that top‑1 accuracy fails to capture, and suggest that mixed‑precision Q4_K schemes can offer lower divergence than uniform Q4_0 at comparable memory usage.