A JoLT for the KV Cache: Near-Lossless KV Cache Compression via Joint Tucker and JL-Residual Allocation for LLMs
The key-value (KV) cache has become the dominant memory cost of transformer inference. It grows with batch size, context length, and depth, and at long context it, rather than the model weights, sets the ceiling on throughput. Two families of methods reduce it. Low-rank methods factor two-dimensional slices of the cache, either per-head matrices or cross-layer feature blocks, and quantization methods lower the bit-width of every entry. Neither family exploits the fact that the cache at a layer is naturally a third-order tensor whose three axes, the heads, the tokens, and the features, carry ve
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 59%jagmarques/nexusquant →
- PossiblePossibly related (embedding) · 58%xcena-dev/maru →
- PossiblePossibly related (embedding) · 56%pythongiant/KVBoost →
- PossiblePossibly related (embedding) · 55%Zefan-Cai/KVCache-Factory →
- PossiblePossibly related (embedding) · 47%Picovoice/llm-compression-benchmark →
- LinkedLinked via arxiv author · 85%Rahul Krishnan →
“A JoLT for the KV Cache: Near-Lossless KV Cache Compression via Joint Tucker and JL-Residual Allocation for LLMs”
- LinkedLinked via arxiv author · 85%Volker Schulz →
“A JoLT for the KV Cache: Near-Lossless KV Cache Compression via Joint Tucker and JL-Residual Allocation for LLMs”
- FuzzySimilar title/name (fuzzy) · 87%LMCache/LMCache →
“Fuzzy title match (0.94): “A JoLT for the KV Cache: Near-Lossless KV Cache Compression ” ≈ “LMCache/LMCache””