THE INTERNET IS THINKING
Earlier sources: AI infrastructure
AI infrastructure comprises the compute, storage, serving systems, and operational tools used to train and deploy models. Follow inference engines, distributed training, observability, and the costs and constraints of running AI workloads.
SYMTRI organizes observations from public sources into a living map. Connections reflect shared subject matter; they do not establish causation or endorse a source.
Open in the map ↗41 classified signals in the fourteen-day window. These counts include signals awaiting readable evidence.
Earlier sources
Up to ten sources with readable evidence, ordered by their feed timestamp. These archive sources can be older than the live fourteen-day window. This list is a sample, not a measure of total activity. Dates distinguish paper publication, repository creation, model/dataset activity, Hacker News posts, and KEV catalog additions. “First archived” records when SYMTRI first stored the signal.
- arXiv · Published · First archived
Finite-Sample Distribution Theory and Efficient Large-Scale Inference for Online Quantile Regression ↗
This paper studies online quantile regression for large-scale and streaming data using Stochastic SubGradient Descent (SSGD) with constant learning rates. Classical offline inference for quantile regression is computationally and memory intensive. Existing works of online inference for quantile regression provide only asymptotic guarantees and typically require sub-exponential tail conditions for distribution theory. To bridge these gaps, we introduce new techniques to prove a quenched central limit theorem (CLT) and finite-sample Gaussian approximation for SSGD under a finite-moment assumptio…
- arXiv · Published · First archived
DiMOS: Doob-Guided Inference-Time Multi-Objective Search for Scientific Design ↗
Scientific design often requires jointly satisfying multiple objectives and constraints. Pretrained masked diffusion models provide a generative foundation for this task, but fine-tuning them to meet these objectives and constraints incurs additional training costs, motivating inference-time guidance with frozen models. However, such guidance faces two challenges: pass-or-fail constraints and black-box reward models may provide no useful gradients, while jointly satisfying multiple requirements can leave a small feasible region, making feasible designs difficult to find within a limited infere…
- GitHub · Repository created · First archived
shawnshekari/strixite ↗
LLM inference engine written from scratch in HIP for AMD Strix Halo (gfx1151) and Qwen3.8-Flash-Next - ~50 tokens/s out to 492k context
- GitHub · Repository created · First archived
xxDoman/strata-gfx906 ↗
Strata v0.1.43 engine (Qwen3.8-Flash-Next) on AMD gfx906 — Instinct MI50 / MI60, Radeon VII. Docker image + web configurator with the gfx906 rocBLAS solution table (+9.1% prefill, measured), expert-tail-skip toggles, and the community benchmark with its report header fixed on AMD. OpenAI/Anthropic API, image input.
- GitHub · Repository created · First archived
christopherowen/dgx-spark-networking ↗
Switchless RoCE collectives, NCCL profiles and fabric tooling for DGX Spark inference recipes
- Hacker News · Posted on Hacker News · First archived
Ask HN: Where can a solo dev still find a moat in LLM inference? ↗
Hacker News discussion.
- GitHub · Repository created · First archived
perkel666/MegaCapybara ↗
The fastest inference engine for Qwen3.8-27B on the NVIDIA RTX 5090: up to 500 tokens/s for one agent and up to 2,000 tokens/s for many, contexts up to 1M tokens, and a launcher that shows what every setting costs. Windows and Linux.
- GitHub · Repository created · First archived
Yamz-Labs/kyojin ↗
Kyojin: the Yamz inference engine for AMD Strix Halo (ROCm, gfx1151), built on ExLlamaV3. Runs 300B-class MoE models on one 128 GB mini PC.
- arXiv · Published · First archived
Amortized Structured Stochastic Variational Inference for Gaussian Process Latent Variable Models ↗
Many machine learning methods aim to approximate the lower-dimensional manifold on which the data lives. A desirable feature of such methods is that they should capture the epistemic uncertainty of this learned manifold. One model that achieves this is the Gaussian Process Latent Variable Model, in which a Gaussian Process (GP) mapping from the latent space provides an estimate of the uncertainty of the manifold. However, the effectiveness of this uncertainty estimation is limited by the mean-field variational approximation between the GP inducing points and the latent variables. In this work,…
- Hacker News · Posted on Hacker News · First archived
Rai: CPU-only LLM inference engine in pure Rust ↗
Hacker News discussion.
Live window recorded . This is the ingestion observation time, not the publication or discovery date of each source.
How to assess evidence about AI infrastructure
Check each original source for its methods, release status, limitations, and supporting data. A repository announcement, a preprint, and a published study provide different kinds of evidence. SYMTRI’s subject classification helps discovery; it does not independently validate the source’s claims.
See the collection and counting methodology ↗ · Read the weekly synthesis ↗
Related threads
Explore related regions
These navigation suggestions are part of the map’s editorial structure, rather than measured evidence of a connection.