Search headlines, summaries and articles to connect the dots.
Kimi K3.1 Pro from Moonshot AI is now available on Amazon Bedrock. Learn how to get started through the OpenAI-compatible Chat Completions, Responses, and Converse APIs, optimize inference with explicit prompt caching, and use the model as a coding assistant in OpenCode.
TL;DR We serve Meta’s Muse Spark Open, an 816B-parameter mixture-of-experts model, on a single TPU v7 host of four chips, with SGLang running on the TorchTPU PyTorch backend. At the... The post Optimizing Muse Spark Open on TPU v7 with SGLang-TorchTPU appeared first on PyTorch.
As AI writes more code, the bottleneck has become human-driven code reviews. Code Lens serves to aid that task by augmenting the review outside of line-level AI feedback. Check it out and let me know what you think. Thanks.Try it on a public PR: npx @blong8334/codelens pr https://github.com/expressjs/express/pull/7574 Comments URL: https://news.ycombinator.com/item?id=50446651 Points: 1 # Comments: 0
On Qualcomm Adreno GPUs, scalar flash attention was limited to 8 rows per workgroup when head size exceeds 128 to prevent register spilling and performance degradation. This change improved performance significantly, reducing execution time from several seconds to milliseconds and enabling completion of the test-backend-ops case.
NVIDIA Nemotron 3.5 Super VL, a 120B-parameter multimodal vision-language model, is now available in Amazon SageMaker JumpStart. Deploy the NVFP4 or BF16 variant in a few steps, then run text, image, and video inference for document intelligence, computer-use agents, and multimodal agentic workloads.
Autonomous vehicle (AV) developers need reasoning models that can operate within the compute and latency constraints of an onboard system. Larger models provide...
arXiv:2611.08500v1 Announce Type: new Abstract: Graph Transformers improve long-range node-to-node communication through global or structure-aware interactions. However, improving cross-node communication does not determine how computations produced at different depths should be combined. Standard residual streams accumulate successive computations with fixed unit coefficients shared across nodes. This fixed aggregation is a residual-interface constraint: once intermediate contributions have been produced, the interface cannot explicitly reweight them by node. We hypothesize that this constraint can create a depth-wise aggregation mismatch when the relative utility of these intermediate contributions varies across nodes and structural contexts. To study this hypothesis, we formalize Graph Transformer residual computation as a causal node-wise history of graph-propagation and feed-forward network (FFN) contributions, making depth aggregation an explicit interface choice. We realize node-adaptive aggregation over this history with Attention Residuals (AttnRes) while preserving the backbone's graph-propagation and auxiliary-state machinery. Block AttnRes reduces the routing cost of long histories relative to Full AttnRes by pooling consecutive contributions. We instantiate the interface in GPS and GRIT and evaluate it on all five ECHO tasks. Both variants achieve lower mean absolute error (MAE) than their independently tuned backbones on every task, and at least one obtains the lowest mean among all compared methods in each task. Routing-only donor-swap interventions support the mismatch hypothesis, while additional ablations examine the key design choices. Together, these results support node-adaptive depth aggregation as a useful complement to cross-node communication in long-range graph reasoning.
Hi, this is a package I developed for keeping track of short toy-model development cycles and explaining what changed between runs.The core idea: commands run through the package, and their declared parameters (or injected parameters with --substitute) and outcomes go into a dependency-free ledger stored in the project. Because that ledger lives in the project directory, it has worked well for passing context between different agents. I’ve also found some use for it in CI work. Comments URL: https://news.ycombinator.com/item?id=50417782 Points: 3 # Comments: 0
The update qualifies calls to math functions like isnan and signbit with std:: to ensure compatibility with C++ standard library overloads, addressing issues on NetBSD 11.99.9/x86_64 with gcc 14.4.0. Additional C math function calls are standardized using std:: prefixes (e.g., std::fabs, std::copysign) instead of non-existent std::fabsf variants, improving accuracy by keeping computations in double precision. The change results in a minor behavioral difference with a relative error of at most 1.4e-7, well below test tolerances.
The update introduces support for 3D convolution (conv_3d) on Hexagon hardware by generalizing the existing conv_2d implementation. It leverages the HMX tiled path, folds kernel dimensions into a virtual row, and uses a shared solver with an is3d flag. The host computes unfold divisors to avoid device-side division, prevents DMA queue overflow, and improves tile size selection based on VTCM usage. Additional changes include handling arbitrary positive strides, preserving load/shuffle paths for small strides, and fixing compiler warnings.
The metal backend's kernel_group_norm_f32 was updated to correctly handle tensors with ne03 > 1 and non-contiguous inputs by dispatching one threadgroup per (group, i03) pair, computing per-batch statistics, clamping group element count for incomplete groups, and supporting strided access via separate strides for source and destination. The fix also restricts GROUP_NORM to f32 inputs and improves performance through specialized pipeline variants.
Amazon SageMaker Inference now supports GPU partitioning with NVIDIA Multi-Instance GPU (MIG), which divides one GPU into hardware-isolated partitions so you can run a different model in each or take a right-sized fraction of a newer accelerator. This post shows how two optional API fields place one model per partition, and what we measured against a whole older GPU.
arXiv:2611.07132v1 Announce Type: new Abstract: We present an automated method for auditing text-to-image generators for representational bias against ground-truth demographic benchmarks. Our approach adapts the racial proxy variables used in U.S. antidiscrimination law to provide a fine-grained comparative analysis of variations in racial representation in generated images. We classify each generated image by race and then compare the model's distribution to publicly available demographic benchmark data to identify patterns of over- and under-representation. We also measure skin tone using CIELAB values and calculate cosine similarity amongst groups of images in order to capture biases that don't show up in demographic comparisons such as differences in image quality across races and skin tones. We report on experiments testing three models (Imagen 4 Fast, Stable Diffusion 3.5 Large Turbo, and Flux Schnell) using three categories of proxies (geographic, occupational, and surname) and 50 variants within each category. We find notable variation across the models as well as by proxy category. For example, Imagen 4 Fast overrepresents white classified images more than the other models tested and produces images with lighter, more homogeneous skin tones. Imagen 4 Fast also had the largest representational disparity for Black demographics among surname and geographical prompts. Stable Diffusion 3.5 Large Turbo produces results that overall diverge most from census data but yield the most diverse range of skin tones. Our method yields a generalizable and legally-grounded auditing tool that surfaces detailed information about model outputs without relying on implicit normative definitions of fairness.
The latest update to llama.cpp (v1.2140) adds support for the `truncate=false` parameter in YaRN, enabling more accurate frequency interpolation for models like gpt-oss and certain PLaMo-3 variants by preserving non-integer interval boundaries. The change includes updates to GGML operations and CPU backend handling, with CUDA backend support, new tests, and refactoring of RoPE helpers into internal headers. Default behavior remains `truncate=true` for backward compatibility.
The Vulkan implementation of the Fast Walsh-Hadamard Transform (FWHT) has been enhanced to support block widths up to 8192, using shared-memory shaders for larger blocks, and now includes F16 input capability via shader-float16, with pipelines created only when device limits allow. This update aligns Vulkan with CUDA's capabilities and improves efficiency by eliminating the need for F32-to-F16 conversions.
arXiv:2611.07159v1 Announce Type: cross Abstract: Proof-of-Possession (PoP) establishes that an executor controls an artifact (key, token, credential, or capability), but such control alone determines neither the executor's relational profile nor the causal history of an execution occurrence. We separate PoP from Proof of Relationship (PoR), the semantic property that one execution occurrence validly continues another, and from authorization, which is occurrence-sensitive. The foundational change is in the semantic domain of authorization: from holders and authority-bearing artifacts to execution occurrences situated in causal histories. We give authorization models an observation-based occurrence verdict and a separate transition-admissibility relation; kernel inclusion yields a partial order on observation-kernel classes. Building on Provenance Identity Continuity (PIC) and Proof-of-Continuity (PoC), we classify executors by authorization-relevant equivalence relations whose quotients form relational profile spaces, with positive predicates over profile transitions forming a distributive lattice. This adds relational attenuation to authority attenuation: along a valid causal history, $C_{i+1}\subseteq C_i$ and $\rho_{i+1}\Rightarrow\rho_i$. We prove dual monotonicity, combined closure, and origin relational closure. Two occurrences of the same authenticated executor, with the same profile and possession evidence, need not be authorization-equivalent, and within a valid PIC lineage a deputy's independent authority cannot be imported outside the origin context. Finally, we prove that the executor-dependent decision factors through the relational profile and is invariant under sound mechanisms establishing it: successor-side PoP is a possible evidence mechanism, not a necessary premise of authorization. Under explicit Witness Assumptions, a boundary-witnessed checkpoint construction realizes the premises without successor-side PoP.
arXiv:2611.06977v1 Announce Type: new Abstract: Reproducible LLM inference requires that a request produces the same output regardless of the other requests in the batch. Existing solutions pay for this in different ways: batch-invariant kernels constrain every operator, and isolating prefill with fixed-shape decode ({our CoRun-style baseline}) gives up shared prefill compute and pads decode. We present BlockLock, which keeps shared batched prefill and pins only the numerical path of the protected request: it fixes the geometry that the request sees, with {two modes: BlockLock-Rows uses fixed-width rows and retains batched decode of all requests; BlockLock-Pack uses terminal-anchored packing with an isolated dummy segment, then extracts the protected request's KV state for target-only decode. Under a stated per-deployment contract, both modes preserve the target's output bitwise when its companions change.} Across five {dense} models (Qwen3-8B/14B, Llama-3.1-8B-Instruct, and Gemma-3-4B/12B-IT) and three single-GPU deployments (NVIDIA A6000, A100, and H100), we evaluate our approach on both tinyBenchmarks and BFCL{; we also include initial tensor-parallel experiments on two NVIDIA A6000 GPUs. Both modes preserve target sequences and Top20-logit bits in the reported tests.} At equal delivered work, {BlockLock-Rows} reduces latency by 53.5--55.0\% and improves throughput by 115.2--122.2\% relative to vLLM Batch-Invariant; compared with batch-invariant kernels, it needs no custom kernel implementations and constrains only the protected requests.
Google DeepMind has launched Gemini Omni 1.2 Flash, introducing native 15-second video generation, improved reference adherence, stronger consistency across frames, multi-turn conversational editing, more natural speech, and cinematic camera movements. The model is now generally available via the Gemini API and Gemini for business, priced at $0.07 per second for 720p video—30% lower than its predecessor. It supports scalable workflows, including draft generation at lower resolutions, iterative edits, and upscaling to 1080p or 4K. Use cases include product explainers, social ads, virtual try-ons, and branded content, with applications across Google AI Studio, Google Cloud, Google Vids, Flow, the Gemini app, and Google Ads.
Learn how Amazon Marketplace evaluates A+ Content quality at scale on Amazon SageMaker AI by rendering each product page as a single snapshot, scoring it with a vision-language model fused with OCR readability signals in a CatBoost classifier, and using SHAP to turn each decision into prioritized, actionable recommendations for selling partners.
NVIDIA has introduced four new open-weight checkpoints for its Cosmos 3 model family—Cosmos3-Nano-Transfer-Auto, Cosmos3-Nano-Sim-Auto, Cosmos3-Nano-Sim-Transfer, and Cosmos3-Nano-Sim-Bimanual—enabling interactive world simulation and multi-sensor, multi-view driving scene generation. Each model is a post-trained variant of Cosmos 3 Nano with 16B trainable parameters and is based on OpenMDW1.1, allowing commercial and non-commercial use. The checkpoints support applications in robotics and autonomous driving by generating synchronized camera and LiDAR data, enabling streaming simulations, translating simulator controls into photorealistic video, and predicting visual outcomes from robot actions. They are designed to be adapted using custom data and training recipes, with support for offline data generation, causal distillation, and interactive rollouts. Resources include technical reports, demos, and notebooks for inference and adaptation.
