ON1 (G116 V8): 38μs Black-Box AI Memory Retrieval on Virtual Chip ISA
The ON1 G116 v8 introduces a quantum-inspired virtual memory chip designed for advanced AI memory retrieval. This new architecture allows for observable latency in memory, compute, and ANN search processes, enhancing the performance of large language models. Users can test the system's latency decomposition through a public verification endpoint.
- ▪The G116 v8 features a latency-separated architecture that breaks down vector retrieval into three stages: Fetch, Compute, and Search.
- ▪Latency for the Fetch layer is approximately 0.1 to 0.5 microseconds per operation, while the Compute layer ranges from 0.4 to 2 microseconds.
- ▪The Search layer currently uses brute-force methods with a latency of 3 to 10 milliseconds per operation.
Hacker News (AI / LLM) files mainly under ai. We currently carry 3,312 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | GitHub |
| Canonical URL | https://github.com/ON1-Hao/ON1 |
| Publication time | Fri, 29 May 2026 15:00:09 +0000 |
| Retrieval time | 2026-05-29T15:10:01.524Z |
| Last seen | 2026-05-29T15:10:01.524Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | Pl3GEaIGcfXD |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
ON1 G116 v8: 38μs Black-box AI Memory Retrieval on Virtual Chip ISA (Latency-Separated Fetch/Compute/ANN) — Live Tunnel Inside G116 v8: Quantum-Inspired Virtual Memory Chip – A New Paradigm for Black-Box AI Retrieval Unlike any conventional chip. G116 v8 introduces a quantum-inspired virtual ISA that makes memory, compute, and ANN search latency observable – not just a single opaque query time. Built for the next generation of LLMs (llama.cpp, real‑time RAG, natural language grounding).
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.