Knowledge Graph
Graph explorer
Search resolved entities, walk their edges, and read the sentence behind every one.
Entities25 of 207,987
- large language modeltechnology1,048 mentions
- robotic manipulationmarket834 mentions
- artificial intelligencetechnology739 mentions
- reinforcement learningtechnology492 mentions
- density-functional theorytechnology386 mentions
- Transformertechnology372 mentions
- vision-language-action modeltechnology355 mentions
- agentic AItechnology353 mentions
- Vision-Language Modeltechnology321 mentions
- U.S. Food and Drug Administrationorganization320 mentions
- Microsoftorganization291 mentions
- Googleorganization277 mentions
- NVIDIAorganization265 mentions
- Model Context Protocoltechnology232 mentions
- machine learningtechnology204 mentions
- MarketsandMarketsorganization199 mentions
- Claudeproduct192 mentions
- AI agenttechnology188 mentions
- ChatGPTproduct178 mentions
- Anthropicorganization177 mentions
- integrated sensing and communicationtechnology176 mentions
- Amazon Web Services, Inc.organization174 mentions
- OpenAIorganization172 mentions
- diffusion modeltechnology170 mentions
- IBMorganization163 mentions
Entity
key-value cache quantization
technology4 mentionslast seen Nov 6, 2026
A method to reduce memory bandwidth requirements in long-context LLM decoding by storing quantized key-value caches in dense on-chip non-volatile memory.
Relationships 13
- key-value cache quantizationapplies tolarge language model decoding90% confidence1 source
- key-value cache quantizationdepends onband-norm-witness bound88% confidence1 source
- key-value cache quantizationdepends onper-vector normalization85% confidence1 source
- key-value cache quantizationdepends onrandomized rotation85% confidence1 source
- key-value cache quantizationdepends onfixed-range converter85% confidence1 source
- key-value cache quantizationdepends onsubtractively-dithered INT8 quantizer85% confidence1 source
- Per-Channel Reductiondepends onkey-value cache quantization85% confidence1 source
- key-value cache quantizationdepends onanalog crossbar85% confidence1 source
- runtime risk observabilityapplies tokey-value cache quantization85% confidence1 source
- meter-driven gatingapplies tokey-value cache quantization83% confidence1 source
- WitCert: Sound Runtime Risk Observability and Gating for KV-Cache Quantizationauthoredkey-value cache quantization82% confidence1 source
- key-value cache quantizationsupersedesKIVI K2V270% confidence1 source
- key-value cache quantizationsupersedesKVQuant70% confidence1 source
Sources
Select a relationship to read the sources behind it.