Figure: a matrix of six systems against the five control-plane stages SELECT, PLACE, MOVE, ATTEND and OBSERVE. vLLM is the substrate: it allocates at PLACE and executes at ATTEND, and is what the other systems run on. PNM-KV optimises SELECT: it selects which KV or token pages are needed before paying the movement cost, using a processing-near-memory accelerator, and reports up to 21.9 times throughput improvement in its own benchmarks, arXiv 2511.00321, their reported result and not independently verified here. CacheWise optimises SELECT and PLACE: it predicts future KV reuse from agent and tool-call behaviour, combining prefix-aware scheduling with reuse-aware eviction, and reports 2 to 2.6 times fewer KV-cache evictions and up to 3.5 times faster agent session completion in a vLLM implementation over its own collected coding-agent traces. LMCache optimises PLACE and MOVE: KV persistence, reuse and movement across tiers and engines, including pinning, lookup, cleanup, movement, compression, batched movement, compute and I/O pipelining, cross-engine cache transfer, and prefill/decode disaggregation. TraCT optimises MOVE: rack-scale KV sharing and transfer over CXL, implemented on NVIDIA Dynamo with direct GPU to CXL operations behind a rack-wide prefix-aware cache. Tutti optimises MOVE: efficient GPU to NVMe KV object movement, removing the CPU from the critical path and using GPU io_uring with slack-aware I/O scheduling, and against GDS-enabled SSD-backed LMCache reports 78.3 per cent TTFT reduction under strict SLO constraints, 2 times higher achievable request rate, 27 per cent lower serving cost, and near-DRAM performance at much greater capacity, arXiv 2605.03375. This package contributes one cell, at PLACE: residency persistence, plus 34.15 points to LFU at 32 gibibytes, simulated and provisional. No system in the survey optimises OBSERVE. Every figure quoted is external literature, that system's own reported result, cited and not reproduced here. This is a map of how the pieces could compose, not a claim that any system is inferior or that a gap exists.

Figure 10.1 · External literature

The 2026 landscape, placed by the decision each system optimises

Not a ranking, and not a gap analysis. Five specialised 2026 systems mapped onto the five stages of the control plane, to show how the pieces could compose.

What this figure is, and is not. It is a map of how the pieces could compose. It is not a claim that any of these systems is inferior, nor that a gap exists for this package to fill. The field did not leave a gap; it specialised. Each system below solves a different sub-decision well, and every figure quoted is that system’s own reported result, cited and not reproduced here.

Placed by the decision each one optimises

SELECTPLACEMOVEATTENDOBSERVESYSTEMvLLMsubstrateALLOCATESEXECUTESPNM-KV2026OPTIMISESCacheWise2026OPTIMISESOPTIMISESLMCache2026OPTIMISESOPTIMISESTraCT2026OPTIMISESTutti2026OPTIMISESThis packageone resultONE RESULTNobody in this survey optimises OBSERVE — the feedback stage is unclaimed, by everyone, including this package.
2026 system — the stage whose decision it optimisesSubstrate — vLLM, what the others run onThis package — one simulated, provisional result inside PLACENot claimed by that system

What each system optimises, and what it reports

The pieces are specialised, not unified.CacheWise’s tool-call-driven reuse prediction lives inside vLLM’s eviction path and does not decide where a block should physically reside. PNM-KV’s near-memory selection avoids wasted recalls, but selection and cross-tier movement policy remain separate concerns. LMCache spans tiers and engines but does not predict future reuse from agent signals. TraCT solves rack-wide CXL transport but is not a relevance-prediction system. Tutti’s contribution is squarely at the GPU↔NVMe movement layer.

Nobody has built the joint control plane — including this package.Whether a higher-level control plane should sit above these pieces, jointly deciding what is relevant, what will be reused, where it should live and when it should move, is a design question. This package’s only contribution to the map is one cell: residency persistence inside PLACE, +34.15 pts to LFU at 32 GiB, simulated and provisional — a single defect in Revision 1 of that simulator inverted four of five findings.

External literature — chapters/ch10-market.html §10.2. Each figure is that system’s own reported result, cited and not reproduced.