b9844
llama.cpp is a C/C++ implementation for LLM inference with minimal setup and state-of-the-art performance on a wide range of hardware. Release b9844 is an intermediate build of the llama.cpp project f
Knowledge catalogue
llama.cpp is a C/C++ implementation for LLM inference with minimal setup and state-of-the-art performance on a wide range of hardware. Release b9844 is an intermediate build of the llama.cpp project f
Release build b9846 is an intermediate build of llama.cpp, an open-source C/C++ project for LLM inference. The llama.cpp project is the main playground for developing new features for the ggml library
llama.cpp uses continuous build-tagged releases rather than traditional semantic versions. Release b9848 is a specific build from the ggml-org/llama.cpp project, which is an LLM inference implementati
b9849 is a build release from llama.cpp, which enables LLM inference in C/C++ . The release represents an intermediate build version of the llama.cpp library, a widely-used open-source project for run
B9851 is a release of llama.cpp, an LLM inference project written in C/C++ . The release represents a version update in the llama.cpp development timeline maintained on GitHub. This build tag typicall
arXiv:2603.17621v2 Announce Type: replace-cross Abstract: Reinforcement Learning (RL) has emerged as a powerful paradigm for training LLM-based agents, yet remains limited by low sample efficiency, st
arXiv:2606.28361v1 Announce Type: cross Abstract: Multi-step retrieval-augmented generation (RAG) has been widely deployed as LLM-powered web services for complex question answering, where iterative r
arXiv:2606.28471v1 Announce Type: new Abstract: Model capability is the central variable in LLM pre-training, yet is never observed directly: data shapes it prospectively, while evaluation reveals it
arXiv:2606.30128v1 Announce Type: new Abstract: Chain-of-thought (CoT) prompting improves LLM reasoning, but the source is contested: do the intermediate steps help because they carry useful semantic
arXiv:2606.29961v1 Announce Type: cross Abstract: Large Language Model (LLM)-based agents can solve complex procedural tasks by interacting with environments over multiple turns, but this ability typi
arXiv:2606.29540v1 Announce Type: cross Abstract: Large language models (LLMs) can leave subtle stylistic traces in assisted text; one of the most cited is the em-dash (Unicode U+2014). Yet no one has
arXiv:2606.29493v1 Announce Type: new Abstract: Benchmarks for LLM-assisted theorem proving in Lean are often treated as intrinsically reliable because every solved instance comes with a machine-check
arXiv:2606.30566v1 Announce Type: cross Abstract: We discover a behavioral invariant in LLM agents under persistent memory poisoning: in architectures where routing information is retrieved through ob
arXiv:2606.28831v1 Announce Type: cross Abstract: Long-context LLM inference faces a fundamental conflict: head-adaptive compression algorithms (e.g., Top-p nucleus sampling) offer superior accuracy b
arXiv:2606.28916v1 Announce Type: cross Abstract: We introduce GRAB, a constructor-encoder-bridge pipeline for table question answering. Our method lifts relational data into an heterogeneous graph, e
arXiv:2606.29279v1 Announce Type: cross Abstract: LLM agents carry conclusions across steps and sessions in compressed memory, and memory products (e.g., mem0, LangMem) rewrite conversation into store
arXiv:2606.29604v1 Announce Type: cross Abstract: We aim to discover diverse, generalizable perturbations of LLM internals that can surface hidden behavioral modes. Such perturbations could help resha
arXiv:2606.28374v1 Announce Type: new Abstract: LLM agents are increasingly improved without weight updates by evolving a natural-language artifact, such as reflections, workflows, playbooks, cheatshe
arXiv:2606.28620v1 Announce Type: cross Abstract: Fayyazi et al. (2025) recently proposed FACTER, a model-agnostic framework designed to jointly enforce fairness and statistical coverage in LLM-based
arXiv:2606.30304v1 Announce Type: cross Abstract: This paper presents preliminary findings from a UKRI-funded Metascience project comparing three LLM-based approaches, GPT-4o, Mistral, and a bespoke a
arXiv:2606.29997v1 Announce Type: new Abstract: Automatic evaluation of image and video captioning is essential for benchmarking multimodal systems, although standard evaluation metrics show limited a
arXiv:2606.29713v1 Announce Type: cross Abstract: Hallucination is the reliability bottleneck for LLM-based agents, and fact attribution verifiers are the last line of defense -- yet today's verifiers
arXiv:2606.29565v1 Announce Type: new Abstract: A stateless inference server (vLLM, SGLang, TensorRT-LLM) idles between requests while the accelerator waits; a stateful session reclaims that idle time
arXiv:2602.12394v2 Announce Type: replace Abstract: Personalized prompting offers large opportunities for deploying large language models (LLMs) to diverse users, yet existing prompt optimization meth
arXiv:2606.29481v1 Announce Type: cross Abstract: While reinforcement learning (RL) significantly enhances LLM reasoning, its efficacy is severely undermined by Pre-RL data overlap, where RL datasets
b9840 is a release of llama.cpp, a tool for LLM inference in C/C++. The release enables running AI models locally on Windows, Linux, and macOS. This specific build tag likely contains bug fixes, perfo
arXiv:2606.28249v1 Announce Type: cross Abstract: Recently, Large Language Model (LLM)-based Text-to-Speech (TTS) models have achieved remarkable naturalness. However, the standard Supervised Fine-Tun
arXiv:2606.27567v1 Announce Type: cross Abstract: Prompt injection is the top security risk for LLM-integrated applications, yet every defense proposed so far has been broken. We prove this is not a c
arXiv:2502.16886v4 Announce Type: replace-cross Abstract: To reduce memory consumption during LLM inference, a handful of methods have been proposed for KV cache pruning. While these techniques can ac
arXiv:2606.28153v1 Announce Type: cross Abstract: Jailbreak attacks bypass LLM safety alignment, yet their mechanisms remain poorly understood. We provide evidence that attacks do not comprehensively
arXiv:2606.28013v1 Announce Type: new Abstract: Headline type-correctness (TC%) of LLM autoformalization has climbed from sim53% to sim76% in two years, yet this scalar conceals which errors each meth
Learn how TrueFoundry AI Gateway exports OpenTelemetry traces to Arize AX so teams can trace, evaluate, and monitor production LLM and agent traffic without embedding a vendor SDK in every service. Th
llama.cpp b9830 is a release of the open-source LLM inference project enabling local language model execution with minimal setup . The release likely includes backend improvements and optimizations fo
Release b9833 is a build of llama.cpp, an open-source project for LLM inference in C/C++. This release represents an incremental update within the llama.cpp development cycle, following the standard r
b9822 is a release of llama.cpp, a project for LLM inference in C/C++ . As a build version in the ongoing development sequence of the llama.cpp project, this release likely includes bug fixes, perform
B9826 is a release of llama.cpp, an LLM inference project written in C/C++ . llama.cpp enables users to run large language models on consumer hardware without expensive GPUs or cloud infrastructure .
arXiv:2606.26566v1 Announce Type: cross Abstract: Adversarial evaluation of AI systems has matured along four largely disconnected tracks: diffusion-based attacks on text and large language models (LL
b9821 is the latest release of llama.cpp, a C/C++ implementation of LLM inference, which includes updates to allow the application to support --version, --licenses, and --help flags . Pre-built binari
arXiv:2606.26216v1 Announce Type: cross Abstract: We present CyberChainBench, a benchmark for evaluating LLM-based agents on smart contract security across three complementary tasks: vulnerability det
Fireworks AI is now live on EvoSkill v1.3.0! You can now use @FireworksAI_HQ directly with EvoSkill to run fast inference on open models as both the evolution harness backend and the LLM scorer. Along
arXiv:2606.26614v1 Announce Type: cross Abstract: Large language model (LLM) agents enable natural language interaction for scientific visualization (SciVis). Still, prior systems have essentially pri
arXiv:2606.26981v1 Announce Type: cross Abstract: Synthesizing human motion from textual descriptions is essential for immersive digital applications, yet existing methods face a persistent trade-off
team cooked, spicily We’ve designed and built our first AI chip: Jalapeño. Designed from the ground up by OpenAI and brought to production with @Broadcom, Jalapeño is purpose-built for the LLM workloa
arXiv:2606.27288v1 Announce Type: new Abstract: Multi-model LLM systems such as routing, voting, cascades, fusion, and mixture-of-agents are used to beat single-model accuracy. We show that their gain
arXiv:2606.25476v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated remarkable performance across natural language processing tasks, yet their deployment in high-stakes appl
b9786 is a release of llama.cpp, a tool for LLM inference in C/C++ . Llama.cpp is a free and open-source tool that allows users to run AI models locally on Windows, Linux, and macOS . The b9786 releas
B9787 is a build release of llama.cpp, an open-source C/C++ implementation for LLM inference created by Georgi Gerganov. The llama.cpp project enables large language model inference with minimal setup
arXiv:2606.25421v1 Announce Type: new Abstract: Recent studies on world modeling for Large Language Model (LLM) agents typically formulate the learning objective as next-observation prediction. Howeve
arXiv:2606.16497v2 Announce Type: replace-cross Abstract: GPU kernel optimization represents a paradigm where functional correctness is assumed and execution efficiency is the objective. We present da
arXiv:2606.25787v1 Announce Type: cross Abstract: When a large language model (LLM) answers a question about a company, it grounds the answer in retrieved web sources, and those sources decide what th
arXiv:2606.18837v2 Announce Type: replace-cross Abstract: Large Language Model (LLM)-based automatic Multi-Agent Systems (MAS) generation has become a crucial frontier for tackling complex tasks. Howe
arXiv:2606.25632v1 Announce Type: new Abstract: Recent LLM role-playing systems build character agents from novels by extracting characters, scenes, and relations. Yet long-narrative role-playing suff
arXiv:2606.24775v1 Announce Type: new Abstract: Memory for large language model (LLM) agents has rapidly evolved from simple retrieval-augmented mechanisms into a data management system that supports
arXiv:2606.24453v1 Announce Type: new Abstract: Modern coding agents pair LLM generators with various tools, including cheap diagnostics and expensive verifiers. The tool-use decisions are typically g
arXiv:2606.23991v1 Announce Type: new Abstract: What is an agent? What constitutes agency? With the rise of Large Language Model (LLM) systems marketed as ``coding agents'', ``AI co-scientists'', and
arXiv:2606.24779v1 Announce Type: cross Abstract: Birth defects are a major cause of fetal loss, neonatal morbidity and long-term disability. In the subset with suspected genetic etiologies, exome and
arXiv:2606.17698v2 Announce Type: replace Abstract: As LLM-based shopping agents enter production, existing benchmarks fail to capture how a shopper's requirements arrive: stated implicitly in the que
arXiv:2606.24428v1 Announce Type: new Abstract: Experience-driven self-evolution is critical for large language model (LLM) agents to improve through open-world interaction. However, existing experien
arXiv:2606.23961v1 Announce Type: new Abstract: Long-context and agentic LLM workloads push the KV cache past any fixed memory budget, forcing the inference stack to permanently evict tokens at every
arXiv:2606.23797v1 Announce Type: cross Abstract: Graph and multi-agent orchestration frameworks make production large language model (LLM) workflows practical, but they do not by themselves solve con