Knowledge catalogue
Llamacpp, when properly configured on Apple Silicon hardware, demonstrates robust performance and reliability for running language models. The tool can handle varied input requests effectively, making
AI compute resources should not be treated as interchangeable commodities, as different hardware configurations, providers, and architectures significantly impact training costs, inference latency, an
arXiv:2509.22166v4 Announce Type: replace-cross Abstract: The demand for efficient large language model (LLM) inference has intensified the focus on sparsification techniques. While semi-structured (N
Google announced Ironwood, its seventh-generation TPU that is twice as power efficient as the previous generation, alongside specialized hardware designed to support the emerging agentic AI era. Ironw
This article from SemiAnalysis analyzes the total cost of ownership for GPU clusters, likely covering hardware expenses, infrastructure requirements, power consumption, and operational overhead beyond
arXiv:2604.15475v1 Announce Type: new Abstract: Deploying learned multi-robot models on heterogeneous robots remains challenging due to hardware heterogeneity, communication constraints, and the lack
arXiv:2509.23638v2 Announce Type: replace Abstract: Mixture-of-Experts (MoE) models face memory and PCIe latency bottlenecks when deployed on commodity hardware. Offloading expert weights to CPU memor
arXiv:2507.01041v4 Announce Type: replace-cross Abstract: Split learning (SL) is a distributed learning paradigm that can enable computation-intensive artificial intelligence (AI) applications by part
arXiv:2604.11659v1 Announce Type: cross Abstract: Fully homomorphic encryption (FHE) has recently attracted significant attention as both a cryptographic primitive and a systems challenge. Given the l
arXiv:2604.11109v1 Announce Type: cross Abstract: As high-performance computing and AI workloads become increasingly dependent on GPUs, maintaining high performance across rapidly evolving hardware ge
Auto-generated index of all companies mentioned across the wiki.
arXiv:2601.02624v2 Announce Type: replace-cross Abstract: The growing complexity of modern system-on-chip (SoC) and IP designs is making security assurance difficult day by day. One of the fundamental
arXiv:2604.07013v1 Announce Type: cross Abstract: Designing quantum neural networks (QNNs) that are both accurate and deployable on NISQ hardware is challenging. Handcrafted ansatze must balance expre
A lot of projects have come up recently consisting of specific hardware config specialized forks of existing conferencing engines, but they all seem to be made using Claude or OpenAI's biggest frontie
arXiv:2610.11302v1 Announce Type: new Abstract: Training-free sparse attention offers a practical acceleration solution to Diffusion Transformers (DiTs) via reducing computations without fine-tuning.
Nous Research Inc., the developer of the popular Hermes artificial intelligence agent, today announced that it has raised 90 million in funding. Early-stage startup fund Robot Ventures led the Series
arXiv:2610.08231v1 Announce Type: new Abstract: NVFP4 is an attractive datatype for large language model (LLM) inference, offering compact storage and native tensor-core acceleration. However, preserv
arXiv:2610.05578v1 Announce Type: cross Abstract: Multi-camera streaming perception is increasingly deployed on heterogeneous edge platforms shared with co-resident workloads, yet accelerator placemen
arXiv:2610.03797v1 Announce Type: new Abstract: World Action Models (WAMs) leverage pretrained video foundation models for robot manipulation, but their large backbones and video-action co-prediction
I have been running the same midrange card for a couple of years now, and every model release sends me back to the price sheets. The performance gains are real but they keep landing next to price tags
arXiv:2610.01397v1 Announce Type: new Abstract: Dynamic humanoid motions such as flips risk hardware damage due to suboptimal policies, disturbances or sim-to-real gaps. A motion tracking policy offer
Hi all! I am a former SWE who has recently transitioned into inference engineering. I launched a side hustle a few months back and I've just taken it full time due to excessive demand. Its been such a
arXiv:2609.38978v1 Announce Type: new Abstract: Diffusion Transformers (DiTs) have become a dominant architecture for video generation, but their efficiency is limited by the quadratic complexity of f
arXiv:2609.37001v1 Announce Type: cross Abstract: Diffusion Transformers (DiTs) enable high-quality video generation but suffer from substantial inference latency, primarily attributable to the comput
arXiv:2609.34818v1 Announce Type: cross Abstract: AlphaFold2 is written in JAX, so the same inference code compiles and runs unchanged on CPUs, GPUs and Google Cloud TPUs. That portability makes the a
arXiv:2609.33965v1 Announce Type: cross Abstract: We describe a methodology for estimating the per-token energy cost of cloud-hosted large language model (LLM) inference, separating between input (pre
arXiv:2510.05632v2 Announce Type: replace-cross Abstract: With the widespread adoption of Large Language Models (LLMs), the demand for high-performance LLM inference services continues to grow. Multi-
arXiv:2609.30629v1 Announce Type: cross Abstract: Mission-critical UAVs increasingly rely on split vision-language model (VLM) perception under tight onboard-resource and wireless-communication constr
Sometimes it’s easy to forget that this sub and others like it are probably the extreme minority when it comes to this hobby. Most people, I would think, don’t use or can’t afford one good GPU, let al
Every rent-vs-buy thread I read has confident people on both sides, but not many actually show the numbers. So I finally ran the numbers for our own decision. Posting the working here in case it is us
NV‑Reason‑CT is a purpose‑built vision‑language model for volumetric CT that uses a full 3‑D Vision Transformer encoder coupled with a Qwen 3.5‑4B language model to generate radiologist‑style chain‑of
arXiv:2510.09022v2 Announce Type: replace Abstract: Recent Machine Learning (ML) approaches have shown increased performance on benchmarks at the cost of escalating compute demands. Hardware, algorith
arXiv:2609.15130v1 Announce Type: cross Abstract: woma is a real-time foundation model for gastrointestinal endoscopy: a network trained without labels on about a million endoscopy frames, from which
ggml-cuda: fallback to F32 on device without BF16 hardware acceleration (#28846) ggml-cuda: fallback to F32 on device without BF16 hardware acceleration: (Nvidia >= AMPERE, AMD >= RDNA3 or = CDNA) app
ggml-cpu : disable PCH and fix CACHE_LINE_SIZE ambiguity to fix heap corruption (#28882) Disable the ggml-cpu precompiled header and remove the std::hardware_destructive_interference_size branch from
arXiv:2609.12412v1 Announce Type: cross Abstract: Foundation models, including large language models, vision-language models, and time-series foundation models, are increasingly deployed on embedded a
arXiv:2609.11133v1 Announce Type: new Abstract: Datacenter GPU power is the binding constraint on LLM serving capacity, and production serving has shifted to prefill/decode (PD) disaggregation. Deploy
Privacy have been concern of many of us to have their own hardware to run llms, and here's another reason why: two mathematicians spent a year cracking one of the hardest problems in math and fed ever
arXiv:2603.24595v2 Announce Type: replace-cross Abstract: Large language model (LLM) inference systems rely on CUDA kernels for core GPU computations, yet the interface between models and kernels is i
arXiv:2608.29540v1 Announce Type: new Abstract: This paper introduces NepScript Genesis, a Neural Architecture Search (NAS) framework for automated Generative Adversarial Network (GAN) discovery, appl
arXiv:2608.24154v1 Announce Type: cross Abstract: Real-world deployment of traffic surveillance systems is bottlenecked by geographic domain shift, in which models trained in one city underperform whe
arXiv:2608.23101v1 Announce Type: cross Abstract: Recent progress in the field of TinyML has demonstrated that low-power hardware based on microcontrollers can achieve bird species monitoring in real
arXiv:2608.20572v1 Announce Type: new Abstract: Convolutional Neural Networks (CNNs) face a dual challenge: vulnerability to adversarial attacks and prohibitive training cost. Adversarial training is
arXiv:2608.20350v1 Announce Type: cross Abstract: Traditional industrial agents rely on modular pipelines, including Router, Retriever, Planner, Executor, Responder, Reviewer, and other components. Th
arXiv:2608.19881v1 Announce Type: cross Abstract: Radio frequency (RF) fingerprinting authenticates wireless devices from hardware-induced I/Q impairments, typically with deep learning feature extract
arXiv:2608.17515v1 Announce Type: cross Abstract: Background: Large Language Models (LLMs) are increasingly being applied to Software Engineering (SE) tasks, achieving high accuracy across problems su
arXiv:2608.17874v1 Announce Type: new Abstract: Visual-inertial SLAM on low-power edge platforms is constrained by the cost of dense feature extraction and loop closure. Prior GPU ports of ORB-SLAM tr
Four Tesla V100s from 2017 matched my RTX 5090 on single-request Qwen 3.8 decode. Repo: https://github.com/dnv2003/v100-skinny https://i.redd.it/5ws2ak3uqckh1.gif The 5090 was not being held back. It
arXiv:2608.15636v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have demonstrated remarkable capabilities in the field of embodied AI, but their high computational cost and limit
arXiv:2608.15602v1 Announce Type: cross Abstract: While binary quantization theoretically promises extreme compression and acceleration for Large Language Models (LLMs), existing research often overlo
arXiv:2604.03781v2 Announce Type: replace Abstract: Colorectal cancer screening critically depends on colonoscopy, yet existing platforms offer limited support for systematically studying the coupled
arXiv:2608.10506v1 Announce Type: cross Abstract: Accurate pre-deployment estimation of CNN inference cost--energy, latency, and peak memory--is increasingly critical as models are deployed on resourc
arXiv:2608.10795v1 Announce Type: new Abstract: Successful mutation strategies in evolutionary code search may contain reusable knowledge that is useful beyond a single run, and in some cases may tran
arXiv:2608.08469v1 Announce Type: new Abstract: Existing streaming multimodal models process observations incrementally but still follow a turn-based prefill-then-decode pattern, making them non-duple
Been benchmarking DSv4 Flash 0731 on a Flow Z13 (Ryzen AI MAX+ 395, Radeon 8060S / gfx1151, 128GB LPDDR5X) for the past week. Figured I'd share what actually works and what doesn't — there are a lot o
arXiv:2608.08285v1 Announce Type: new Abstract: We present Ego-OSCAR, an open-hardware, low-cost, head-mounted stereo-inertial capture device for egocentric data collection in the wild. EgoOSCAR pairs
🦔Nvidia announced agreements yesterday with the six biggest names in private capital, Apollo, Blackstone, BlackRock, Brookfield, Goldman Sachs, and KKR, to raise over $500 billion so its own customers
arXiv:2608.06803v1 Announce Type: cross Abstract: Ising machines are emerging as promising hardware for combinatorial optimization. With recent advances in CMOS Ising technology, they are becoming att
Ultra-High Interactivity on NVIDIA GPUs? TileRT InferenceX Can TileRT software on NVIDIA GPU compete with Cerebras, Groq LPU, SambaNova? Batch Size 1, Disaggregated engine, High throughput prefill eng
arXiv:2608.04502v1 Announce Type: cross Abstract: Attention--Feed-Forward Network (FFN) Disaggregation (AFD) is emerging as a promising architecture for serving Mixture-of-Experts (MoE) language model