SuperLocalMemory V3.3 implements a cognitive memory taxonomy with mathematical forgetting and multi-channel retrieval, reaching 70.4% on LoCoMo in zero-LLM mode.
QJL: 1-bit quantized JL transform for KV cache quan- tization with zero overhead
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
representative citing papers
HyperQuant unifies Hadamard transform, optimal lattice quantization, and entropy coding to outperform prior schemes on LLM weight and KV cache quantization down to 1.7 bits per scalar while preserving quality on a 19B DiT model.
A tiered KV cache architecture computes per-head per-step error bounds on quantized attention and uses adaptive fallback to guarantee bounded or exact outputs relative to FP16 reference.
At 4-bit budget KQV wins on KL divergence, geometric K error and 6D distance with unconditional K-V asymmetry; QKQV wins geometrically at other budgets because the Jensen-amplified variance inflation from QJL on K does not bind.
Fused compressed-domain int4 attention on Apple Silicon delivers 48x speedup and 3.2x KV cache compression for 128K-context 70B models while matching FP16 token predictions.
AXELRAM performs attention on quantized KV cache using a fixed orthogonal-transform codebook, reducing multiplications by 102.4x and fixing sign-sensitivity spikes via gradient-free calibration.
TurboQuant achieves near-optimal vector quantization distortion for both MSE and inner products via random rotation and per-coordinate scalar quantization, with a formal proof that it matches lower bounds within a factor of approximately 2.7.
UltraQuant applies 4-bit KV caching with TurboQuant-style rotation and custom AMD kernels to context-heavy agent workloads, delivering 3.47x P50 TTFT reduction in cache-pressured rounds and 1.63x throughput gain over FP8.
Hierarchical two-speed shared-weight recurrence in Transformers shows a sharp performance gap compared to independent layer stacking in empirical language modeling tests.
citing papers explorer
-
SuperLocalMemory V3.3: The Living Brain -- Biologically-Inspired Forgetting, Cognitive Quantization, and Multi-Channel Retrieval for Zero-LLM Agent Memory Systems
SuperLocalMemory V3.3 implements a cognitive memory taxonomy with mathematical forgetting and multi-channel retrieval, reaching 70.4% on LoCoMo in zero-LLM mode.
-
HyperQuant: A Rate-Distortion-Optimal Quantization Pipeline for Large Language and Diffusion Models
HyperQuant unifies Hadamard transform, optimal lattice quantization, and entropy coding to outperform prior schemes on LLM weight and KV cache quantization down to 1.7 bits per scalar while preserving quality on a 19B DiT model.
-
Runtime-Certified Bounded-Error Quantized Attention
A tiered KV cache architecture computes per-head per-step error bounds on quantized attention and uses adaptive fallback to guarantee bounded or exact outputs relative to FP16 reference.
-
Statistical Inference and Quality Measures of KV Cache Quantisations Inspired by TurboQuant
At 4-bit budget KQV wins on KL divergence, geometric K error and 6D distance with unconditional K-V asymmetry; QKQV wins geometrically at other budgets because the Jensen-amplified variance inflation from QJL on K does not bind.
-
Open-TQ-Metal: Fused Compressed-Domain Attention for Long-Context LLM Inference on Apple Silicon
Fused compressed-domain int4 attention on Apple Silicon delivers 48x speedup and 3.2x KV cache compression for 128K-context 70B models while matching FP16 token predictions.
-
AXELRAM: Quantize Once, Never Dequantize
AXELRAM performs attention on quantized KV cache using a fixed orthogonal-transform codebook, reducing multiplications by 102.4x and fixing sign-sensitivity spikes via gradient-free calibration.
-
TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate
TurboQuant achieves near-optimal vector quantization distortion for both MSE and inner products via random rotation and per-coordinate scalar quantization, with a formal proof that it matches lower bounds within a factor of approximately 2.7.
-
UltraQuant: 4-bit KV Caching for Context-Heavy Agents
UltraQuant applies 4-bit KV caching with TurboQuant-style rotation and custom AMD kernels to context-heavy agent workloads, delivering 3.47x P50 TTFT reduction in cache-pressured rounds and 1.63x throughput gain over FP8.
-
Hierarchical vs. Flat Iteration in Shared-Weight Transformers
Hierarchical two-speed shared-weight recurrence in Transformers shows a sharp performance gap compared to independent layer stacking in empirical language modeling tests.