Quest (Long-context / context-window extension): superseded — cited as a baseline and beaten by newer methods. 2 paper(s) critique it, 2 beat it on benchmarks — #17 of 53 most-superseded. Sub-problem: cluster led by StreamingLLM. Newer alternatives in the same sub-problem include BA-Att, CSAttention, TCA-Attention, Dynamic Hierarchical Sparse Attention (DHSA).

Long-context / context-window extension

Quest

Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference

Superseded baseline#17 of 53 most-superseded · first seen Jun 16, 2024

Superseded — cited as a baseline and beaten by newer methods

2 papers critique it · 2 beat it on benchmarks

What papers say

Verbatim critique sentences, each from a paper that cites Quest as a baseline.

Despite the relatively low overhead, Quest lacks sophisticated design in the retrieval strategy, thus suffers from noticeable performance degradation.

— A$^2$ATS: Retrieval-Based KV Cache Reduction via Windowed Rotary Position Embedding and Query-Aware Vector Quantization

“Quest~tang2024quest maintains high accuracy but at the cost of substantial memory usage due to the need to cache the entire KV cache, eventually leading to OOM on long sequences.”

— LaCache: Ladder-Shaped KV Caching for Efficient Long-Context Modeling of Large Language Models

Beaten on benchmarks

Head-to-head results where a newer method reports beating Quest. Values are copied from the source paper's tables — verify against the cited paper.

A2ATS beats Quest
86.3 vs 78.4
Accuracy · [MegaBeam-Mistral-7B-512K, Sparsity ~0.062]
A$^2$ATS: Retrieval-Based KV Cache Reduction via Windowed Rotary Position Embedding and Query-Aware Vector Quantization
DHSA beats Quest
71.5 vs 68.2
48K · [48K tokens]
Long-Context Modeling with Dynamic Hierarchical Sparse Attention for On-Device LLMs

What to use instead

Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.