Now / public snapshot
5 August 2026 · Tel Aviv

What is actually on the bench.

A hand-curated record of the current focus and public open loops. This is intentionally dated; it is a working state, not a claim of permanent priority.

Primary focus / 01

Make the MTP drafter smaller than the overhead it is meant to remove.

The primary study is StudentSV: a half-width MTP block with its own 32,768-token output head, trained for the real speculative-decoding path instead of inheriting the target model's full 248,320-row projection.

The study is concluded, and the answer is no—for a functional reason, not a size one. The verifier-as-oracle audit sorted every compression into two families: fidelity cuts (precision) cost at most 1.9 acceptance-retention points even under severe shift, while function cuts—pruning, low-rank, and the distilled StudentSV itself—keep 97% on calibration-register text and pay 10–19 points where the text actually shifts. Parameters serving rare content accumulate no mass on any finite calibration sample. The recipe that survives is zero-training: trim the vocabulary to the model's own 32k hottest rows, quantize to NVFP4, verify full-vocabulary—1.82× at 9B, 2.88× composed at 27B, measured end-to-end in memra, distribution-exact by construction. Harness at avifenesh/hqmtp; the paper draft is written and in internal review rounds.

Subject
Qwen3.5-9B · co-trained MTP → StudentSV
Methods
Small-vocabulary head · half-width block · chain distillation
Standard
Separate training signal, acceptance, FLOPs, and measured wall time.
Parallel threads / 02

The studies and systems that keep touching each other.

The model experiments need a runtime, and the runtime keeps generating better research questions. These are the nearest active loops.

A / apparatus memra

The Rust + CUDA inference engine that exposes the real costs of MTP drafting, verification, quantization, expert spill, and Blackwell kernel choices. Renamed from bw24; v0.69 ships prebuilt binaries and serves official FP8 checkpoints with out-of-the-box MTP speculation at 2.6–2.8× plain decode.

public · v0.69
B / training recipe-lab

Layer-loop weight sharing plus ε=λ/(N√L) residual scaling, tested from zero in eleven pre-registered rounds. Data-constrained at d=768 the looped model beat FLOPs-matched vanilla in all three mixer families—attention 3/3 seeds, pure SSM 2/2, hybrid 2/2; seven paired runs, zero sign flips. The hybrid rounds isolated the rule "loop the state-mixer, never the retriever". The d≥1024 rung is next.

public · scaling rung next
C / retention mem-retrofit

Product-key memory grafted post-hoc onto dense Qwen3-4B, five sequential update rounds against LoRA. The retrofit is free at lr/10; the published forgetting advantage never cleared a confidence interval in 12 of 12 tries. A powered ~30-seed run is what can change the verdict.

public · concluded at n=3
D / compression REAP × quant

First physical artifact public on Hugging Face: Hy3-REAP-Layer103p5, a receipt-bound expert overlay selected on routing displacement. The public REAP50 mask was rejected at the screening gate (0.24 domain-macro vs the unpruned 0.73); layer-balanced pruning with private calibration holds 83.5% retention at the 100GB cap. Measured per-projection damage across seven formats now feeds one global allocator that chooses precision and pruning together under the byte ceiling.

working paper 02
E / review revuto

A local PR reviewer that learns from maintainer feedback, with the model supplier and repository kept replaceable.

updated 04 Aug
F / maintain Valkey GLIDE

Review, API and reliability work across a large multi-language client, plus the support and release details that never appear in feature lists.

maintainer

Working on the same edge? Compare notes.