ZeroHour
DashboardNewsCVEsExploitsIncidentsAIBriefAnalyticsEntitiesWatchlistIOCsAsk the feedSourcesFeeds & APIKiosk mode

Search: “latency”

251 stories

Searchkeywordsmart Sortlatesthotimportancerelevance
DomainAllCyberAIWindow24h3d7d30dAllIn the wildImportant onlyShow duplicates
CategoryAllAI tools & infra 97AI industry 54AI research 49Model release 41AI safety & security 37AI policy 6
SeverityAllcritical 0high 0medium 29low 0info 255

Show HN: Nari Qwen3-TTS and Qwen3-ASR – High accuracy, low latency and cost

Nari Labs claims top Coval voice AI benchmark rankings with low-latency, low-cost Qwen3-ASR and Qwen3-TTS inference endpoints.

Nari Labs says its Qwen3-ASR Fast endpoint ranks #1 in Coval's time-to-final-segment latency (p50 44 ms) with 3.6% WER at $0.12/hour, behind only AssemblyAI Universal 3.5 Pro on accuracy. Its Qwen3-TTS Fast ranks #2 in time-to-first-audio (p50 63 ms) and #1 in WER at 3.8%, priced at $10 per 1M characters. The company reports beating the official Qwen3 TTS Flash Realtime endpoint (8.8% WER, 692 ms median TTFA) and Baseten's dedicated endpoint (6.0% WER, 101 ms). Public beta APIs are moving to paid general availability with $20 in credits for existing accounts.

Hacker News · security · 2d agoAI tools & infraHN 21↑ · 7 comments1

Rapidly scaling online storage to serve over 1 billion ChatGPT users

OpenAI's Habitat online storage platform now handles over 70 million requests per second and 500 PB of data for 1 billion users.

OpenAI details the evolution of Habitat, its online storage platform backing ChatGPT and other products, which began in mid-2024 as a Python client-side library over Azure Cosmos DB. Habitat now processes more than 70 million requests per second, serves over 500 petabytes of data across nearly 40 geographic regions, and supports over 1 billion users weekly. By mid-2025 the client library approach became brittle, so OpenAI moved Habitat into a standalone service to centralize deployments, observability, and multi-tenancy reliability. This is part one of a two-part series; a future post will cover read optimization and scaling the Azure Cosmos DB partnership.

OpenAI News · 6d agoAI tools & infra1

harshatheg/Qwen-2.5-1B-RLCD — new model trending #30 on Hugging Face

A community MLX inference engine evaluates constrained JSON schema fields in parallel on Apple Silicon, reporting 5.6-7.0x latency speedups with guaranteed schema validity.

The repository harshatheg/Qwen-2.5-1B-RLCD appeared at #30 on Hugging Face trending, but its content describes Parallel Constrained Decoding, an MLX-based inference engine for structured extraction and classification on Apple Silicon Macs. Benchmarked with mlx-community/Qwen2.5-1.5B-Instruct-4bit on an M4 Max, it reports 5.6x-7.0x latency reductions (e.g., 1,900 ms to 270 ms for a 28-field support triage task) with 100% syntactic validity and calibrated field-level probabilities. The engine prefills a single KV-cache, broadcasts it across all schema fields, and slices logits to valid candidate tokens for enum fields with up to 255 choices.

Hugging Face trending models · 1d agoAI tools & infra

RetroThinker: Enabling Retrospective Thinking in Speech LLMs

RetroThinker is a post-training framework letting the Moshi speech LLM self-correct reasoning mid-stream, adding 11% GSM8K accuracy at similar latency.

Researchers introduce RetroThinker, a multi-stage post-training framework that equips the Moshi speech LLM to verify and forward-correct chain-of-thought steps during streaming inference. It combines supervised fine-tuning on curated retrospective thinking data with length-based direct preference optimization (DPO). On GSM8K it achieves an 11% absolute accuracy gain over non-retrospective baselines at comparable latency.

arXiv cs.AI / cs.LG / cs.CL · 6d agoAI research1

PACE: Perceived-Latency-Aware Cascading Service Routing and Filler Control for QoE-Efficient Retrieval-Augmented Dialogue Serving

PACE cuts perceived latency in retrieval-augmented dialogue serving via cascading routing and filler control, reaching 0.41s P95 under load.

PACE is a serving framework for retrieval-augmented dialogue that optimizes Perceived Time-to-First-Response (PTFR) under quality and cost constraints. It combines a load-adaptive cascading router, a joint path-filler controller, and volatility-aware cache admission, deployed on a humanoid-robot sales service. On 75k CarQA requests, the cascade halved pure-LLM P95 PTFR (0.29s vs 0.53s) and the adaptive controller reached 0.41s P95, 2.4x better than RAG at high load; filler calls dropped 94% and stale answers fell from 86% to 0%.

arXiv cs.AI / cs.LG / cs.CL · 7d agoAI tools & infra

Build Low-Latency Multilingual Voice Agents: Open Weights & Full Deployment Control with NVIDIA Magpie TTS

NVIDIA's Magpie TTS open-weight multilingual speech model enables low-latency voice agents with full deployment control.

Hugging Face's blog highlights NVIDIA Magpie TTS, an open-weights multilingual text-to-speech model designed for building low-latency voice agents. The open licensing gives developers full deployment control, allowing self-hosted multilingual speech for agentic applications. The post walks through building voice agents with the model.

Hugging Face Blog · Aug 10, 2026Model release

AI Infra Summit: NVIDIA Vera Rubin and DSX Platform Advancements Showcase Energy Efficiencies of Optimizing Tokens Per Watt for AI Factories

At AI Infra Summit, NVIDIA showcased Vera Rubin and DSX gains up to 1.4x tokens per megawatt, plus Annapurna, d-Matrix, and Pinterest partnerships.

Ian Buck's AI Infra Summit keynote before 8,000+ attendees emphasized validated agentic tokens per megawatt as the emerging AI infrastructure metric. Announcements include Amazon's Annapurna Labs collaborating on NVHBM custom high-bandwidth memory, d-Matrix integrating NVLink Fusion with Raptor XPUs, and Pinterest using Blackwell plus Dynamo inference software for conversational visual discovery. Lambda reported 23% better performance per watt with DSX MaxLPS on Blackwell servers, running 19 nodes on a 16-node power budget. NVIDIA says DSX MaxLPS combined with Groq 3 LPX on Vera Rubin NVL72 targets up to 35X token throughput per megawatt versus GB200 NVL72 for 2-trillion-plus-parameter models.

NVIDIA Blog · 1d agoAI industry

SlipSense: Multimodal Tactile Learning for Low-Latency and Generalized Slip Detection

SlipSense fuses a 32x32 piezoresistive array and MEMS accelerometer to detect robotic grip slips within 23.1 ms, generalizing zero-shot across platforms.

SlipSense is a multimodal tactile slip-detection framework built on TacV5, a sensor combining a 32x32 piezoresistive array at 240 Hz and a 3-axis MEMS accelerometer at 8 kHz. It performs modality-specific encoding, intra-sensor fusion, and cross-modal attention with causal temporal prediction at 240 Hz. On a 1.4-million-frame dataset spanning 37 objects it achieves 96.7% Macro F1 with a false-positive rate below 1.6%, detecting 76% of slip events within 23.1 ms. Trained solely on UMI data, it transfers zero-shot to a Tesollo dexterous hand across unseen objects, sensor units, and platforms.

arXiv cs.AI / cs.LG / cs.CL · 2d agoAI research

A Three-Layer Caching Architecture for Low-Latency LLM Web Search on Commodity CPU Hardware

OreoLook's three-layer Redis caching architecture cuts redundant LLM calls and embedding work for CPU-hosted web-search answer generation.

The paper describes a three-layer caching architecture for OreoLook (formerly lixSearch), an open-source LLM answer engine: a Redis session context window with Huffman-compressed disk overflow, a semantic query cache matching rephrasings via embedding cosine similarity, and a URL embedding cache deduplicating embedding computations. Deployed on a single 8-vCPU Intel Cascade Lake server with 30 Hypercorn workers across three containerized replicas, it achieved an 89.3% aggregate Redis keyspace hit rate, 0.1 ms read latency, and 1.38 MB memory overhead. An LRU eviction daemon migrates idle sessions to disk and rehydrates them for resumption hours or days later.

Hugging Face daily papers · Aug 11, 2026AI tools & infra2

Perplexity Details Its GPU Embedding Stack: How Ivy, Tulip and ROSE Serve pplx-embed

Perplexity details its GPU embedding serving stack (Ivy, Tulip, ROSE), which reuses LLM prefill/decode kernels, CUDA graphs, and LazyTensors to cut launch overhead.

Perplexity engineers published a deep dive on the serving infrastructure behind pplx-embed, used across Perplexity Search and its API platform. The stack comprises Ivy (Rust HTTP gateway), Tulip (gRPC scheduling and batching), and ROSE (Runtime-Optimized Serving Engine), which reuses LLM prefill and decode kernels rather than running a separate embedding engine. Optimizations include whole-model CUDA graphs with lazy capture and a LazyTensor abstraction that overlaps CPU batch preparation with in-flight GPU work. Benchmarks are reported against vLLM v0.22.0 in BF16, with FlashAttention 4 generally fastest but FlashInfer 3 winning on Qwen-based models at very long sequence lengths.

MarkTechPost · 11d agoAI tools & infra1

Build more natural voice experiences with GPT‑Live‑1 in the API

OpenAI releases GPT-Live-1 in the API, a full-duplex voice model that handles interruptions natively and delegates reasoning to backend models.

OpenAI launched GPT-Live-1 in the API, a single-model full-duplex voice system that listens and speaks simultaneously, replacing chained STT-LLM-TTS architectures. It improves Full Duplex Bench performance by 30 percentage points over GPT-Realtime-2.1 and ranks #1 on Tau3 when paired with GPT-6 Astra at medium reasoning effort. Early partner Speak reported nearly 80% fewer interruptions in language tutoring. The API release costs $0.05 per minute for the front-end voice layer and supports telephony, native ASR transcripts, keyword biasing, and expanded voice and language options.

OpenAI News · 7d agoModel release1

ChatGPT Images 2.5: Faster, more precise, but not the same for everyone

OpenAI released GPT-Image-2.5 (Flare and Sunburst variants), cutting image generation latency up to 50% and improving multi-round edit consistency.

OpenAI launched GPT-Image-2.5 in two API variants: Flare, the faster default with higher quality than GPT-Image-2 at up to 50% lower latency, and Sunburst, built for precise multi-round edits. Both cost $8 per million input and $30 per million output tokens, with new xhigh and max quality tiers; a max-tier 1024x1024 image runs roughly $0.21. Testing found edit consistency strong in ChatGPT Work but inconsistent in Chat, and OpenAI has not documented how ChatGPT routes users between the models.

The Decoder · 8d agoModel release

HoneyRoute: Honeypot-Model Routing for Adversarial LLM Serving

HoneyRoute detects malicious LLM serving requests and diverts them to a honeypot model, reaching F1 0.911 with 38 ms median added latency.

HoneyRoute is an inference-serving layer pairing a streaming router (a frozen 0.8B embedding backbone with per-domain MLP heads) with a dual-implementation honeypot and an analysis loop that converts trapped interactions into attacker fingerprints for router retraining. On a production trace plus a seven-domain attack corpus it matches 96% of a two-tier guard-LLM cascade's F1 at 1/385th of its latency with 0% evasion under 13 adversarial transformations. Diverting malicious traffic cuts production token consumption under GCG-suffix flooding by 97.8%, and loop training raises detection F1 to 0.933.

arXiv cs.CR · 9d agoAI safety & security

PARSER: Read in Parallel, Reason in Depth for Long-Context LLM Agents

PARSER uses parallel reader subagents and an RL-trained lead agent for long-context QA, beating baselines and cutting latency up to 11x.

The PARSER paper decouples reading from reasoning: frozen subagents each read one document chunk in parallel while an RL-optimized lead agent iteratively broadcasts queries and aggregates evidence in scatter-gather rounds. On multi-hop QA with 7K to 896K token contexts, a 4B-backbone PARSER beats the strongest sequential memory baseline by 5.7 points on average and 12.0 points at 896K tokens, and a 9B version surpasses DeepSeek-V4-Pro by 6.3 points. Controlled experiments show robustness to evidence position, order, and distance perturbations, with inference latency reduced by up to 11x.

Hugging Face daily papers · 11d agoAI research1

ShallowStream: Index Shallow then Answer Deep for Streaming Video Understanding

ShallowStream builds streaming-video retrieval indexes from shallow MLLM layers, cutting per-frame prefill latency by up to 52.1x.

ShallowStream is a framework for streaming video understanding with multimodal LLMs that uses the model's shallow layers to simultaneously encode frames and maintain an always-on lightweight retrieval index via shallow-layer KV caches, avoiding full-depth prefill for every incoming frame. At query time, shallow-layer attention scores plus a diversity-aware selection strategy retrieve relevant context frames. It reports performance on par with the strongest existing streaming methods while reducing per-frame prefill latency by up to 52.1x and 10-second end-to-end latency by up to 11.9x, with code released on GitHub.

Hugging Face daily papers · 15d agoAI research

NVIDIA Vera Rubin NVL72 Delivers Leading Performance in MLPerf Inference v6.1 Debut

NVIDIA's Vera Rubin NVL72 debuts in MLPerf Inference v6.1 with up to 3.7x higher throughput than GB300 NVL72 and 99% scaling efficiency at 288 GPUs.

In its first MLPerf Inference preview submission, NVIDIA's Vera Rubin NVL72 achieved up to 3.7x higher throughput than GB300 NVL72 on Qwen3-VL and 2.5x on DeepSeek-R1. A 288-GPU GB300 NVL72 submission across four racks reached 99% scaling efficiency on the DeepSeek-R1 offline benchmark. Software optimizations delivered up to 1.6x gains over v6.0, leveraging TensorRT-LLM, vLLM, Dynamo, disaggregated serving, and NVFP4 precision.

NVIDIA Blog · 21h agoAI industry 2 sources

FlashVector: Agent for Hierarchical Model Serving Stack Optimization

FlashVector agent optimizes all layers of Unity's ad-serving stack, delivering up to 2x model-server throughput and 1.98x latency speedup in production.

FlashVector is an agentic system that optimizes performance across GPU kernels, ML framework computation graphs, model servers, and on-demand feature processing. Deployed in Unity's Vector advertising platform, it achieved up to 2x model-server throughput increase, 1.98x latency speedup, and 1.6x feature-store throughput gain. Optimizations spanned NVIDIA Triton's C++ codebase and the Python feature transformation service, demonstrating extensibility beyond single-kernel tuning.

arXiv cs.AI / cs.LG / cs.CL · 1d agoAI research1

Top 5 AI Gateways for Enterprise (2026 Guide)

A 2026 buyer's guide ranks NeuralTrust TrustGate, Kong AI Gateway, and Cloudflare AI Gateway as top enterprise AI gateways for security and governance.

The guide evaluates enterprise AI gateways on security, governance, routing, observability, and agent ecosystem support. NeuralTrust TrustGate ranks first for identity-aware agent governance across models, MCP servers, tools, and agent-to-agent traffic, with SaaS, hybrid, and private deployment options. Kong AI Gateway is recommended for organizations with mature API infrastructure, while Cloudflare AI Gateway emphasizes caching, retries, model fallbacks, and prompt/response guardrails.

GBHackers · 5d agoAI tools & infra

OpenAI's GPT-Live-1 API lets developers build apps that talk and listen at the same time

OpenAI's GPT-Live-1 API enables full-duplex speech apps, outperforming GPT-Realtime-2.1 with 0.8s turn-taking latency at $0.05 per minute.

OpenAI released GPT-Live-1 as a developer API for full-duplex speech, allowing applications to listen and talk simultaneously; it already powers ChatGPT voice. Benchmarks show 80.1% on full-duplex interactivity versus 45.4% for GPT-Realtime-2.1, turn-taking latency of 0.8 seconds versus 1.4 seconds, tool-calling accuracy of 87% versus 60%, and a 32% pass rate on a banking voice-support benchmark versus 12.4%. The model costs $0.05 per minute, ships twelve new voices, provides ASR transcripts and response text, and is already in production at Yelp for phone-based reservations.

The Decoder · 6d agoModel release1

ChatGPT Sketch turns your bad drawings into detailed AI images

OpenAI launched ChatGPT Images 2.5 with a Sketch feature that turns user doodles into images, plus 50% lower latency.

OpenAI released ChatGPT Images 2.5 and a new Sketch feature, activated by typing @Sketch, that lets users draw doodles inside ChatGPT and use them as image generation prompts. The update claims more natural lighting, richer textures, better multi-turn instruction following, and up to 50% latency reduction versus Images 2.0. Users can also leave inline comments on parts of an image to request specific edits. It is available for ChatGPT, ChatGPT Work, and Codex users on desktop, mobile, and web.

The Verge · AI · 8d agoAI industry1

TRACE: Trajectory-robust Admission with Evidence Ordering for Efficient GUI Agents

TRACE, a training-free visual token pruning framework, cuts GUI agent inference latency and memory while keeping trajectory-wide visual evidence reusable.

TRACE is a training-free framework for trajectory-robust admission and coverage-aware evidence ordering that prunes high-resolution screenshot tokens accumulated in GUI agent trajectories. It ranks visual evidence using a query-independent layout-derived interaction prior combined with instruction relevance and feature novelty, and reserves part of the budget for native tokens distributed across the screen to repair spatial coverage. A monotone KV contraction incrementally compresses retired frames into compact session state, avoiding repeated visual encoding or pruning. Experiments across six GUI benchmarks and diverse models verify effectiveness under tight budgets, with source code to be released.

Hugging Face daily papers · 8d agoAI research

Architecting memory and storage in the AI era

Analysis argues AI inference shifts data-center bottlenecks to memory and storage, urging balanced compute, memory, storage, and network architecture over raw compute.

MIT Technology Review, citing Tirias Research principal analyst Jim McGregor, argues that AI inference and agentic workloads make data movement the key constraint, elevating memory and storage from background hardware to strategic assets. The piece says RAG and real-time inference require continuous data retrieval and caching that legacy infrastructure cannot support. It frames infrastructure planning as a business decision balancing performance, efficiency, cost, and scalability in healthcare, finance, and customer-facing AI.

MIT Technology Review · AI · 12d agoAI industry