Explore tools, prompts, skills, news and resources related to GPU 第5页.
Prompt works related to GPU 第5页
Latest articles, prompts, use cases and editorial content about GPU 第5页
Buoyant has released Kinference v0.1.0-alpha.7, an Apache 2.0 control plane that routes requests across vLLM workers on Kubernetes using declarative policies, queue state and KV-cache signals. Self-reported tests showed...
NVIDIA highlights how its open source tools, including AI Aerial and Sionna, are being adopted by researchers to build AI-native 6G networks. The tools enable faster simulations, AI-powered signal reception, and energy-e...
Zyphra released ZYFA, an open-source FP8 and BF16 prefill attention kernel library for AMD Instinct MI355X GPUs. It achieves 1.16-1.76x speedups over AMD's AITER on real model activations, with lower FP8 error. The...
AWS SageMaker Inference now supports NVIDIA Multi-Instance GPU (MIG) partitioning, allowing a single physical GPU to be divided into isolated partitions for deploying multiple models or right-sizing capacity. This featur...
Thinking Machines Lab has released Inkling 2 Small, a sparse Mixture-of-Experts model with 594B total and 17B active parameters, supporting text and image input with a 1M-token context. It scores 31 on the Artificial Ana...
XStack is a new benchmark that evaluates AI agents on migrating entire machine learning repositories from PyTorch on NVIDIA GPUs to JAX on Google TPUs. The benchmark requires agents to deliver a working JAX repository th...
AutoCompress is a new framework that integrates hardware and workload constraints directly into differentiable architecture search for LLM pruning. It jointly optimizes global and per-layer structure using serving-engine...
Thinking Machines released Inkling 2 Small, a 594B-total/17B-active multimodal MoE, trained from scratch in 68 hours on 8.4T tokens (NVFP4). It scores 31 on the Artificial Analysis Intelligence Index, beating many same-s...
STAG-Net is a new lightweight head pose estimation method that uses structure-aware attention over landmark groups, achieving state-of-the-art accuracy among landmark-based approaches on standard benchmarks. It requires...
NVIDIA's Vera CPU achieves industry-leading agent speed and capacity per watt, enabling 1.6x more agents per watt than the fastest x86 CPU and 2x faster agent speed than the most energy-efficient x86 CPU. Partners i...
Amazon Marketplace developed a multi-model fusion system on SageMaker AI to evaluate A+ Content quality holistically. The system renders full product pages as snapshots, uses a Vision-Language Model for semantic scoring,...
ServerBench is a new benchmark that evaluates coding agents' ability to design complete, specialized LLM serving systems. Agents are scored on a dollars-per-dollar metric, balancing latency-qualified token value aga...
This paper investigates which training and calibration data help three open models solve ARC-AGI-2 tasks offline. The authors built a corpus of executable rules and synthetic tasks, but found that fine-tuning on real tas...
A new open-weight agent, SARBLOH, demonstrates that spatial perception, not planning, is key to interactive reasoning on ARC-AGI-3. Its zero-parameter perception engine converts raw grids into object inventories and geom...
OpenAI released GPT-Image-2.6, a new image generation model family available as two API models: Flare for speed and Sunburst for detail. The update introduces GIF output, SVG export, markup-guided edits, and a complexity...
Together AI introduced Together Compiler (TKCC), an agent-driven system that continuously re-optimizes inference as production traffic changes. It uses coding agents to rewrite a model's forward pass)Skip and a pers...
Google Research has introduced Agile Deliberation, a human-in-the-loop framework for building image classifiers around subjective concepts like 'healthy food' or 'clickbait'. The framework uses Gemini...
The roundup covers OpenAI's autonomous security pipeline, which it says validated and generated patches for 948 Linux kernel local privilege-escalation vulnerabilities at a $1.2M API cost. It also reports Moonshot r...