A modular sparse-attention framework with CPU KV offloading and layer-wise RoPE adjustment runs Llama-class models on 3M-token contexts on a single 48GB GPU without training.
Flash-decoding for long-context inference, 2023
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
InfiniteHiP: Extending Language Model Context Up to 3 Million Tokens on a Single GPU
A modular sparse-attention framework with CPU KV offloading and layer-wise RoPE adjustment runs Llama-class models on 3M-token contexts on a single 48GB GPU without training.