model releases

common : gracefully fallback on unsupported regex patterns in JSON schema (#26939) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/42018860 macOS/iOS: macOS

CUDA: adding switch points per HW and quant type to tune the mvq->MMQ decode crossover (#26079) CUDA: runtime GGML_CUDA_MMVQ_MAX to tune the mvq->MMQ decode crossover Add a runtime override of the mul

server: (router) lazy-load startup_models after main setup (#27424) server: (router) lazy-load startup_models after main setup only allow is_first_load to populate it nits nits 2 Website: https://llam

CI: Use LLVM's OpenMP over MSVC_DEBUG_non_redist on Windows (#26678) CI: Use LLVM's OpenMP over MSFT_DEBUG_non_redist on Windows Currently, we ship the non-redist debug version of microsoft's libomp.

metal : dequant kv cache only for large batches (#27438) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/42031082 macOS/iOS: macOS Apple Silicon (arm64) mac

vulkan: FA MMQ should use fp32 for Q quantization calculations (#27413) Codex found that qd could be a denorm and 1/qd would overflow. Website: https://llama.app Attestations: https://github.com/ggml-

mtmd: add --mmproj-device argument (#23255) feat: add --mmproj-device arg & backwards compatible MTMD_BACKEND_DEVICE env var feat: load mmproj device backend immediately, add -mmdev shortflag fix: its

metal : clamp K extent in tensor API mat-mat kernel for K not a multiple of 32 (#27450) The Tensor API mat-mat path of kernel_mul_mm (GGML_METAL_HAS_TENSOR) fed a static K=32 tile to the matmul2d op o

TP: enable tensor split for LFM2/LFM2MOE (#26993) Assisted-by: deepseek-v4-flash Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/42096995 macOS/iOS: macOS A

llama.cpp : bump version to 0.2.0 (#27498) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/42207505 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silic

ci : run ccache-clear as the last step of release jobs (#27503) ci : run ccache-clear as the last step of release jobs Assisted-by: pi:llama.cpp/Qwen3.8-27B update disabled job too to force rebase Co-

model: use ggml_rope_set_offset() (#27382) model: use ggml_rope_set_offset() partially apply to deepseek2 Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/42

Banger paper from Google DeepMind. It's on the very hot topic of model routing. Routers assume the value estimate is free. Working out which specialist handles a query best costs money too, and it is

arXiv:2608.19385v1 Announce Type: new Abstract: Historical Arabic manuscript transcription is not only a recognition problem. A usable scholarly system must cope with shifting hands and layouts, prese

arXiv:2608.20107v1 Announce Type: new Abstract: Recent advances in generative video models have significantly improved visual realism in video object removal, yet evaluation protocols still focus on m

Brace yourselves. We just entered a new era of frontier multimodal models. DeepSeek-V4-Flash-Vision-Exp advances multimodal agent performance. Also, pay attention to Ox Alpha 1M token contexts with te

I recently bought a 32GB V100 off eBay and thought I was all set with rudimentary tests showing zero issues. But then I started seeing weird VRAM-related errors in llama.cpp. I sic'ed Claude on it, to

arXiv:2608.19677v1 Announce Type: cross Abstract: Prefix caching avoids prefill only when a repeated request returns to a server that still holds the prefix KV. Cache-blind balancing disperses that re

arXiv:2606.23487v2 Announce Type: replace Abstract: Medical vision-language models (VLMs) such as BiomedCLIP generalize broadly, but adapting them to a clinical service is as much a safety problem as

arXiv:2608.20305v1 Announce Type: new Abstract: Myocardial scar segmentation from single-stack late gadolinium-enhanced cardiac magnetic resonance (LGE-CMR) imaging has been a longstanding and clinica

arXiv:2608.19652v1 Announce Type: new Abstract: As LLM-based agents are deployed for longer and higher-stakes tasks, their memory systems continue to have crucial gaps. While existing memory benchmark

arXiv:2512.07847v2 Announce Type: replace Abstract: Benchmarking has been the cornerstone of progress in computer vision, natural language processing, and the broader deep learning domain, driving alg

arXiv:2608.19380v1 Announce Type: new Abstract: While modern autonomous driving systems excel at perception tasks such as object detection and trajectory prediction, they lack the high-level causal re

Welcome to the first Cloud CISO Perspectives for August 2026. Today, Chris Betz explains why the AI era makes it more important than ever to lean into security fundamentals.As with all Cloud CISO Pers

arXiv:2608.19632v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) embed governing partial differential equations directly into the training loss, offering a promising alternativ

arXiv:2608.19207v1 Announce Type: new Abstract: Production deployments of Multimodal Large Language Models (MLLMs) increasingly rely on system messages to govern model behavior. Yet existing benchmark

arXiv:2508.19008v3 Announce Type: replace Abstract: Building on a human-led thematic analysis of clinical life-story interviews (> 150,000 words) with inpatients with Borderline Personality Disorder,

arXiv:2608.19389v1 Announce Type: cross Abstract: Automated market makers (AMMs) are a cornerstone of decentralised finance (DeFi). Constant product markets with concentrated liquidity, such as Uniswa

arXiv:2608.20338v1 Announce Type: new Abstract: Large Language Models (LLMs) increasingly require selective removal of harmful or sensitive knowledge, called unlearning, yet existing methods and bench

arXiv:2608.20204v1 Announce Type: new Abstract: Legal work, with its heavy reliance on processing large amounts of text, is often considered one of the domains most exposed to the use of LLMs. Contrac

arXiv:2608.19817v1 Announce Type: cross Abstract: Conventional convolutional kernels are typically defined on fixed discrete grids, limiting their ability to accommodate heterogeneous local structures

arXiv:2608.19760v1 Announce Type: cross Abstract: Audited against causal ground truth from executed replay in a single-agent tool environment (ALFWorld), none of the step-level credit signals used to

arXiv:2608.20210v1 Announce Type: cross Abstract: Small language models are usually built like large ones and then squeezed onto a CPU afterwards. We did the opposite: we fixed the target first, one u

debating whether we should make it an official plugin, but you can try installing it here to try with these commands: claude plugin marketplace add anthropics/claude-plugins-community claude plugin in

arXiv:2608.20114v1 Announce Type: new Abstract: Mobile manipulation requires a robot to predict how locomotion and arm motion jointly alter future observations and control. Existing world-action model

DeepSeek today debuted a new addition to its flagship V4 series of large language models. On launch, V4 Flash Vision Exp is only available via the Chinese startup’s paid developer platform. The compan

https://github.com/deepseek-ai/deepseek-harness/releases/tag/dsh-v0.1.1-rc.1 The DeepSeek adapter adds the multimodal visual understanding model DeepSeek-V4-Flash-Vision-Exp. It also supports configur

Bloomberg: DeepSeek unveils an experimental multimodal version of its V4 Flash model, saying it nears the performance of Anthropic's Opus 4.8 on multimodal agentic tests — DeepSeek unveiled an experim

DeepSeek-V4-Flash-Vision-Exp is now live on the DeepSeek API Platform! 🚀 🔹 This experimental multimodal model matches DeepSeek-V4-Flash on text capabilities—including agents, reasoning, and world know

When using DeepSeek Pro on Ollama, you'll see that the underlying cost is more significant. But if you actually track the usage, you'll actually find that, at least in my benchmarks, I save a lot of t

arXiv:2608.19653v1 Announce Type: cross Abstract: Autonomous agents for machine learning experimentation must navigate heterogeneous repositories, repair training pipelines, and evaluate candidate imp

arXiv:2608.19248v1 Announce Type: cross Abstract: Monitored quantum circuits exhibit a measurement-induced phase transition between volume-law and area-law entanglement as a function of the measuremen

arXiv:2608.20258v1 Announce Type: new Abstract: Decision tree-based models are widely used in machine learning due to their interpretability and strong empirical performance. However, training decisio

arXiv:2603.21875v2 Announce Type: replace-cross Abstract: Speech deepfake source verification systems aims to determine whether two synthetic speech utterances originate from the same source generator

arXiv:2509.08022v3 Announce Type: replace-cross Abstract: Aligning large language models (LLMs) with diverse human values is essential for safe and effective deployment, yet existing benchmarks often

arXiv:2608.19568v1 Announce Type: cross Abstract: Drafting a new Magic: The Gathering expansion begins before any pick from it has been observed: the complete card list is public, but the draft logs t