Make a Robot Arm Feel Weightless with NVIDIA Holoscan 5
Picture guiding a robot arm by hand while its motors supply just enough torque to support its weight and keep the robot upright. This simple interaction, a...
AI NEWS JOURNAL
Search AI news
Search headlines, summaries and articles to connect the dots.
b12207
A new fast path for d_state=64 has been added to the SSM_SCAN kernel in ggml-cuda, improving generation throughput for Zamba2-7B-Instruct from 11 to 15.1 tok/s—approximately a 35% increase—by eliminating CPU fallbacks for this state size. The change was verified with real-world Zamba2 hyperparameters and maintains correctness, though a separate 28% of scan calls still fall back to CPU due to an undiagnosed issue.
b12208
The ggml library has been updated to make tied selections in the radix Top-K algorithm deterministic on CUDA and Metal backends by replacing atomic compaction loops with a deterministic scheme using simdgroup scans and coalesced memory accesses. This change ensures byte-identical outputs across runs, improves performance by 20-45% on M5 Ultra hardware, and enables deterministic testing for Metal and ROCm. Redundant CUDA kernel resets were removed, and Vulkan/Metal changes were reduced or skipped.
b12179
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.
b12143
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.
Migrating vLLM to the LibTorch Stable ABI
How vLLM migrated its CUDA build and compiled dependencies to the LibTorch Stable ABI, enabling compatible PyTorch upgrades without rebuilding vLLM.
Where Should a KV-Cache Repair Budget Go? Distractor Structure and Contextual Compatibility in Non-Prefix Reuse
arXiv:2611.06397v1 Announce Type: new Abstract: Non-prefix KV-cache reuse encodes retrieved chunks independently and concatenates their caches. To find where a small repair budget should be spent, we vary the chunks around the answer-bearing one (the target) across three 7B-8B models and four datasets of dialogue memory, open-domain QA and API documentation. Reuse loses 19-100% of the context-dependent questions that full prefill answers, and it loses more when the other chunks are of the same kind as the target. Because the recoverable damage is spread over these other chunks, restoring a few of them recovers little, and the budget is better spent on the target. This works through contextual compatibility: recomputing the target against the reused cache beats inserting its full-prefill KV in all seven settings tested, although the recomputed KV stays far from the full-prefill KV. Question attention over reused caches, however, selects the target in at most 18.8% of development questions. A retriever finds it more often, and recomputing its top chunk after moving it next to the question significantly beats InfoFlow-style reordering at the same 5% budget in six of nine open-domain QA and API-documentation settings. On dialogue memory, though, recomputing chunks never significantly beats the token-level selector chosen for each setting.
Configure, Certify, and Operate Kubernetes GPU Clusters with NVIDIA DSX OS
One underperforming GPU can slow an entire distributed training job. The node may pass basic health checks and show normal utilization, leaving operators to...
How NVIDIA Uses AI Agents to Streamline AI Factory Operations
As GPU clusters scale, operations span compute, network, hardware, and scheduling. Site reliability engineers (SREs) often have to examine multiple dashboards...
NVIDIA CUDA 13.5 Brings NVIDIA Vera Rubin GA Support
As artificial intelligence and accelerated computing continue to push the boundaries of what's possible, the latest NVIDIA CUDA release arrives to unlock...
vLLM Delivers Day-0 Support for Kimi K3.1 Pro
vLLM supports Kimi K3.1 Pro on day 0: sparse attention on a KDA hybrid, a packed KV cache with FP8 or NVFP4 latents and MXFP4 index keys, token-sharded prefill, decode context parallelism, and fused low-latency decode.
Build Specialized Agents on a Stack You Control with NVIDIA NemoClaw
Building an autonomous agent requires a model, a harness, and domain-specific tools. To deploy an agent more securely, developers need a runtime that enforces...
b11946
server : add realtime conversation and transcription on /v1/realtime (#31269) * server : add realtime conversation and transcription on /v1/realtime Co-authored-by: Xuan Son Nguyen Assisted-by: Claude Opus 5.5 * examples : default the realtime client to the server port 9931 Assisted-by: Claude Opus 5.5 * server : sample realtime responses right after their own decode Slots respond in turns on one context: sampling at the start of the next step read the logits of whichever slot decoded last, so concurrent sessions mixed their outputs. Assisted-by: Claude Opus 5.5 * move more stuff to server-realtime, making it self-contained * examples : fix the type check of the realtime client Assisted-by: Claude Opus 5.5 * examples : use the model card prompts in the realtime client Assisted-by: Claude O
b11877
vulkan: Add a larger tile size for conv3d (coopmat2 only) (#29920) * vulkan: Add a larger tile size for conv3d (coopmat2 only) This adds a larger tile size, in practice it is only for coopmat2 where we don't need shared memory to store the output (would use more than 64KB). Add some additional representative backend tests. At least, this is what codex came up with from looking at sd.cpp Wan VAE. * only apply large tile size for newer driver versions **Website:** - **Attestations:** - **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b11877/llama-b11877-bin-macos-arm64.tar.gz) - macOS Apple Silicon (arm64, KleidiAI enabled) [DISABLED](https://github.com/ggml-org/llama.cpp/pull/23780) - [macOS Intel (x64)](https://github.com/ggml-org/llama
AnyLanguageModel 1.0 released: a unified Swift interface supporting both local and hosted models, compatible with the entire Apple platform family of operating systems 27
Hugging Face has officially released AnyLanguageModel 1.0, an open-source Swift framework fully compatible with the Apple Foundation Models API. It supports seamless switching between local models (MLX, llama.cpp, Core ML) and hosted models (OpenAI, Anthropic, Gemini, Hugging Face Inference Providers, etc.), and introduces new features such as image input, tool invocation, guided generation, and automatic adaptation of inference chunks.
Reduce hallucinations with Bespoke-Minicheck
Bespoke-Minicheck is a new grounded factuality checking model developed by Bespoke Labs that is now available in Ollama. It can fact-check responses generated by other models to detect and reduce hallucinations.
Tool support
Ollama now supports tool calling with popular models such as Llama 3.1. This enables a model to answer a given prompt using tool(s) it knows about, making it possible for models to perform more complex tasks or interact with the outside world.
An entirely open-source AI code assistant inside your editor
Continue enables you to easily create your own coding assistant directly inside Visual Studio Code and JetBrains with open-source LLMs.
Llama 3 is not very censored
Compared to Llama 2, Llama 3 feels much less censored. Meta has substantially lowered false refusal rates. Llama 3 will refuse less than 1/3 of the prompts previously refused by Llama 2.