b10155
mtmd: support MiMo-V2.5 audio input (RVQ-based model) (#26190) gguf converter for mimo audio fix conv cpp impl nits nits 2 Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple
Knowledge catalogue
mtmd: support MiMo-V2.5 audio input (RVQ-based model) (#26190) gguf converter for mimo audio fix conv cpp impl nits nits 2 Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple
Systematic failures of vision models on semantically coherent subsets, known as error slices, reveal limitations in robustness and evaluation. Existing slice discovery approaches largely model slices
mtmd: fix android build (#26150) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux: Ubunt
metal : add f16 type support to leaky relu (#25981) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFra
CUDA: fix external compilation of q1_0 MMQ (#25778) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFra
hexagon: fix Windows crash when op_poll is enabled (#26029) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) i
Long-horizon execution in Large Language Models (LLMs) remains unstable even when high-level strategies are provided. Evaluating on controlled algorithmic puzzles, we demonstrate that while decomposit
cuda: add sqrt_softplus in topk-moe for dsv4 (#25896) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCF
hexagon: check tensor type when reusing descriptors (#25968) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64)
Add support for Laguna XS.2 & M.1 (#25165) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Li
llama-arch: fix DeepSeek4 APE tensor op (#25945) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramew
ci : fix SYCL package shared library lookup (#25987) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFr
ci : add official website link to release notes (#25728) Assisted-by: pi:llama.cpp/Qwen3.6-27B Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI en
Protecting sensitive data used with AI is a critical part of our commitment to providing advanced and secure cloud infrastructure. Confidential Computing cryptographically protects data in use in hard
Apple's biggest event of the year is nearly here. The company's Worldwide Developers Conference will spotlight updates to iOS, macOS, and all of Apple's other operating systems, and this year's event
Apple has been on its back foot, AI-wise, for the past few years. But in a strange way, playing from behind might not be such a bad move. At WWDC on Monday, Apple appears to be getting ready to reintr
Recurrent Neural Networks (RNNs) are naturally suited to efficient inference, requiring far less memory and compute than attention-based architectures, but the sequential nature of their computation h
sam3.cpp - Meta's SAM 3 in pure C++ with @ggerganov's ggml - Supports SAM 3.1, 3, 2.1, 2 and EdgeTAM - FP16, 4-bit quant (EdgeTAM in 15 MB) - Apple Metal GPU, CUDA, CPU - Text-prompted: 'peach' → ever
Code-switching (CS), the alternation between languages within an utterance, is common in multilingual speech but underrepresented in pretraining corpora. Increasing CS coverage requires finding releva
Discrete diffusion models have emerged as strong alternatives to autoregressive language models, with recent work initializing and finetuning a base unimodal model for bi-modal generation. Diverging f
Long agent traces composed of chains of thought and tool calls accumulate stale content that anchor subsequent generations, and eventually outgrow the context window. Existing scaffolds mitigate it wi
RPC: add -sm tensor (#26610) rpc: allow -sm tensor fix flush for apple rdma move graph_uids to rpc_dispatcher cont : fix conflict cont: stop spinning dispatcher thread remove meta backend change add T
Training a single LLM agent jointly across diverse interactive environments has attracted increasing attention as a route to generalist agents. Existing curriculum and data-selection strategies often
Multilingual self-supervised speech models can benefit from sharing information across languages, but under a matched total pretraining data budget they still fall short of monolingual models. We show
The common paradigm of reinforcement learning with verifiable rewards (RLVR) is to let agents make multiple attempts at a task, and optimize towards the successful ones. This becomes problematic in th
When language models reason in chain-of-thought or exchange free-text intermediates, they serialize structured information into natural language. How much tree-structured compositional content survive
In this paper, we study federated optimization for solving stochastic variational inequalities (VIs), a problem that has attracted growing attention in recent years. Despite substantial progress, a si
RPC: use RDMA completion channel to not spin (#29440) RPC: use RDMA completion queue to not spin add TODO for apple RDMA Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/
Hey experts! I genuinely have this question and would love a general consensus from people actually using these models. LLMs have advanced a lot in benchmarks and in practical usage. Even GPT-4o and G
Enterprise data lakes accumulate tables faster than human stewards can document or classify them, leaving columns with missing descriptions and unassigned governance labels. This documentation debt un
Discrete flow matching generates text by iteratively transforming noise tokens into coherent language, but may require hundreds of forward passes. Distillation uses the multi-step trajectory to train
Evaluating video captioning remains a critical challenge for Visual Large Language Models (VLLMs). Existing metrics primarily rely on matching generated text against ground-truth references. This para
This may be somewhat specific to Qwen3.8 27b and the Apple M5 series, perhaps, but enough of us are running this combo that it's worth tossing out there. GGUF models with MTP have been the fastest way
I used a famous Simon Willison's pelican riding a bicycle prompt on the biggest local LLMs that can run on 128GB Apple Silicon. U used quantizations by Unsloth. Qwen3.8 Flash-Next gives a lot of detai
metal : add fa-vec tunings for M4 (#27875) This adds fa_vec_tuned_table records for Apple M4 to ggml-metal-tuning.cpp. Includes F16, Q4_0, Q4_1, Q5_0, Q5_1, and Q8_0. (M4, 10 GPU Cores) Co-authored-by
Designing effective reward signals for open-domain question answering is challenging because high-quality responses must simultaneously satisfy multiple aspects of answer quality that are difficult to
Recent advancements in large language models have intensified the need for efficient and deployable models within limited inference budgets. Structured pruning pipelines have shown promise in token ef
High-fidelity image-to-3D generation requires a 3D representation that captures both geometry and appearance. To support relighting and integration into standard rendering pipelines, the representatio
Supervised fine-tuning on teacher-generated trajectories is the standard first stage for distilling tool-calling capabilities into deployable models. Post-training pipelines that drive shipped tool-ca
Given OpenRouter.ai was snapped up by Stripe, who do we think would go after the 'GitHib' of AI models? It is a big chunk of change they are looking ($13B). Apple may be a contender to give them a rea
Large language models (LLMs) exhibit a wide range of human-like behaviors, from expressing thoughts and emotions, to engaging in relationship-building with users, to refusing requests and maintaining
Modern AI agents increasingly rely on search infrastructure to execute complex, neuro-symbolic reasoning workflows. These workflows often compile into deeply nested, non-monotonic Boolean queries over
Kernel-based optimal transport (OT) estimators offer an alternative, functional estimation procedure to address OT problems from samples. Recent works suggest that these estimators are more statistica
Machine learning techniques in multi-view settings face significant challenges, particularly when integrating heterogeneous data, aligning feature spaces, and managing view-specific biases. These issu
It's a small experiment of mine to check thinking effort on Qwen and I do have to say xhigh does overthink but I'm not sure if it's bad because the result is rather amazing. Although the prompt was ve
As concerns around data privacy in machine learning grow, the ability to unlearn, or remove, specific data points from trained models becomes increasingly important. While state of the art unlearning
Modern Large Language Models achieve impressive reasoning capabilities with long Chain of Thoughts, but they incur substantial computational cost during inference, and this motivates techniques to imp
Large Language Models (LLMs) have achieved state-of-the-art performance on a broad range of Natural Language Processing (NLP) tasks, including document processing and code generation. Autoregressive L
Continuous diffusion and flow matching models could represent a powerful alternative to autoregressive approaches for language modelling (LM), as they unlock a host of advantages currently reserved fo
Large language models (LLMs) with integrated search tools show strong promise in open-domain question answering (QA), yet they often struggle to produce complete answer set to complex questions such a
The quality of open-weight language models has dramatically improved in recent years. Sharing weights greatly facilitates model adoption by enabling their use across diverse hardware and software plat
Preference alignment has become a crucial component in enhancing the performance of Large Language Models (LLMs), yet its impact in Multimodal Large Language Models (MLLMs) remains comparatively under
Recent diffusion models enable high-quality video generation, but suffer from slow runtimes. The large transformer-based backbones used in these models are bottlenecked by spatiotemporal attention. In
Retrieval-augmented generation (RAG) enhances large language models (LLMs) with external knowledge but still suffers from long contexts and disjoint retrieval–generation optimization. In this work, we
Visual generative models (e.g., diffusion models) typically operate in compressed latent spaces to balance training efficiency and sample quality. In parallel, there has been growing interest in lever
Proactive agents that anticipate user needs and autonomously execute tasks hold great promise as digital assistants, yet the lack of realistic user simulation frameworks hinders their development. Exi
This paper was accepted at the AI4TCI (Workshop on AI for Secure and Trustworthy Critical Infrastructure Systems) Workshop at the International Conference on Availability, Reliability and Security (AR
reminds me of the time Greg Brockman personally downloaded YouTube videos for training purposes, as reported in NYT. 🦔Apple is suing OpenAI for systematic trade secret theft weeks before the IPO. The
Multimodal large language models (MLLMs) have recently shown strong performance in visual understanding, yet they often lack temporal awareness, particularly in egocentric settings where reasoning dep
Long-context handling remains a core challenge for language models: even with extended context windows, models often fail to reliably extract, reason over, and use the information across long contexts