arXiv (All)
open access
The KV Cache Is the New Memory Wall
Autoregressive LLM inference at long context is bounded by memory bandwidth, not arithmetic throughput, and the binding resource shifts from model weights to the Key-Value (KV) cache as sequence length grows. For Llama-3-70B in BF16, the 140 GB weight footprint exceeds the 80 GB HBM of a single acce
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- HDA-MoE: Hybrid Parallelism and Dynamic, Adaptive Scheduling for Mixture-of-Experts with 3D Near-Memory Processing#986013
- Torch-PIM: Automated Profile-Guided PIM Offloading for PyTorch#1128917
- Torch-PIM: Automated Profile-Guided PIM Offloading for PyTorch#1108708
- What Becomes of the Antiferromagnetic String When Long Range Neel Order Is Lost? Exact Results#1104545
- openbmb/RLAIF-V-Dataset#786773
Record · ID 1105413
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive