blend-evicted-kv-into-routed-memory-slots-instead TEC-0097 · proposedBlend evicted KV into routed memory slots instead of droppin
Organizes the KV cache as a fixed-size tree of memory buckets, routes each incoming token to a slot via Gumbel-Softmax, and sigmoid-gates a soft merge of the new key/value with the stored one instead of discarding any token, with a learned
Proposed. Filed by the drafting stage because a paper introduces or tests it. Nobody has vouched for it. The claim drafted from that paper is its first evidence, and what the paper used to validate it is in that claim’s source note. Say whether it held up for you, below.
Organizes the KV cache as a fixed-size tree of memory buckets, routes each incoming token to a slot via Gumbel-Softmax, and sigmoid-gates a soft merge of the new key/value with the stored one instead of discarding any token, with a learned Filed by the drafting stage from ARM: Attention with Routed-Memory for Learnable Sparse Control (2609.24417) with status proposed: the paper introduces or tests it, and the claim drafted from the paper is its first evidence. The paper validated it by: RULER average rose from 8.01 (full attention, OOM at 128K) and 4.88 (StreamingLLM) to 15.12, with 5.78 at 128K where baselines score 0 or OOM; LongBench average 18.02 vs 17.09 full attention and 10.76 StreamingLLM; commonsense average essentially unchanged (71.89 vs 72.27) with slightly worse WikiText perplexity (7.86 vs 7.54); latency and KV memory on par with sliding-window caches.. Nobody has vouched for it; add support or contest it on this page.
Does it work?
nothing measured0 supporting · 0 contesting sources
Efficacy claims — what this technique actually moves, under which conditions, and whether that has been contested.
No efficacy claim filed yet. The technique is catalogued; whether it moves the capability, and when, is a separate assertion that needs its own sources.
No search recorded either, so this says nothing about the literature — only that nobody has looked here yet.
Code
No repository linked yet. Contribute one.
Sources
Whether a technique works is a claim. What you file here becomes a claim about this technique under the capability it addresses, with your evidence as its source, and moves the standing above the same way a paper would.