b9480
B9480 is a release of llama.cpp, an LLM inference project in C/C++ . The release likely contains updates, bug fixes, or feature improvements to the llama.cpp codebase for running large language models
Knowledge catalogue
B9480 is a release of llama.cpp, an LLM inference project in C/C++ . The release likely contains updates, bug fixes, or feature improvements to the llama.cpp codebase for running large language models
Build b9483 is an intermediate release of llama.cpp, the C/C++ inference engine for running large language models locally. This build represents a specific commit snapshot from the ggml-org llama.cpp
arXiv:2606.01813v1 Announce Type: new Abstract: Speculative decoding accelerates inference by having a lightweight drafter propose tokens verified in parallel by the target language model. Block diffu
arXiv:2606.02204v1 Announce Type: new Abstract: Large language model agents achieve strong performance on text-based benchmarks but incur prohibitive inference costs, motivating the use of compact neu
arXiv:2512.10236v2 Announce Type: replace-cross Abstract: Modern ML workloads demand distributing training and inference across multiple GPUs. However, these parallelization techniques often suffer fr
arXiv:2606.02091v1 Announce Type: new Abstract: Block diffusion speculative decoding accelerates LLM inference by predicting all tokens within a block simultaneously for the target model to verify in
arXiv:2511.04791v2 Announce Type: replace Abstract: Modern LLM serving systems must sustain high throughput while meeting strict latency SLOs across two distinct inference phases: compute-intensive pr
arXiv:2606.01756v1 Announce Type: new Abstract: Large vision-language models (LVLMs) achieve strong performance on image and video understanding tasks, but their inference efficiency is constrained by
arXiv:2606.01774v1 Announce Type: cross Abstract: Autoregressive (AR) large language models (LLMs) have achieved broad practical success, but sequential decoding remains a key bottleneck for low-laten
arXiv:2602.03018v2 Announce Type: replace Abstract: Outlier detection (OD) is widely used in practice; but its effective deployment on new tasks is hindered by lack of labeled outliers, which makes al
arXiv:2606.00694v1 Announce Type: new Abstract: Short-term anticipation in egocentric video requires more than recognizing the current scene: a system must infer which object the camera wearer will co
arXiv:2606.02556v1 Announce Type: new Abstract: We introduce HERO'S JOURNEY, a benchmark for rule induction in goal-directed episodic tasks, where agents must infer hidden rules from demonstrations an
arXiv:2606.01934v1 Announce Type: cross Abstract: Large language models achieve remarkable performance via extended chain-of-thought (CoT) reasoning, yet this lengthy process incurs substantial infere
arXiv:2602.18195v2 Announce Type: replace-cross Abstract: Alzheimer's disease (AD) alters brain electrophysiology and disrupts multichannel EEG dynamics, making accurate and clinically useful EEG-base
arXiv:2602.23881v2 Announce Type: replace-cross Abstract: Speculative decoding accelerates autoregressive large language model (LLM) inference by using a lightweight draft model to propose candidate t
arXiv:2606.01336v1 Announce Type: new Abstract: As real-world applications increasingly require processing inputs of 100k+ tokens, the gap between context length and inference efficiency has become a
arXiv:2606.00888v1 Announce Type: cross Abstract: Dynamic Sparse Training (DST) offers a promising paradigm for improving the training and inference efficiency of deep neural networks; however, we fin
arXiv:2602.23204v3 Announce Type: replace Abstract: In this work, we introduce the first framework for Motion-aware Event Suppression, which learns to filter events triggered by IMOs and ego-motion in
arXiv:2606.01839v1 Announce Type: cross Abstract: LLM-based agents resolve a user task through many turns of dependent inference and tool calls, producing a workload whose total cost is unknown when t
arXiv:2606.01803v1 Announce Type: new Abstract: The explosive growth of Text-to-Image (T2I) models, from large-scale versions to lightweight, real-time ones, now faces diminishing marginal returns fro
arXiv:2606.01682v1 Announce Type: cross Abstract: Selecting the best response from multiple small-model samples using a stronger scorer is a simple inference-time strategy, but fails when the small mo
arXiv:2512.10339v2 Announce Type: replace Abstract: Inference-time steering adapts pretrained diffusion and flow models to new tasks without retraining, often utilizing ratio-of-densities construction
arXiv:2606.00102v1 Announce Type: new Abstract: Over the centuries, probability theory has grown from the calculus of games of chance into a central framework for reasoning under uncertainty. This art
arXiv:2606.01908v1 Announce Type: cross Abstract: Test-time adaptation (TTA) can reduce error on new and different data by updating the model on these inputs during inference. However, these updates r
arXiv:2606.00021v1 Announce Type: cross Abstract: Speculative Decoding (SD) accelerates Large Language Model (LLM) inference by employing a lightweight draft model to propose candidate tokens, which a
arXiv:2606.02544v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) have recently emerged as a promising alternative to autoregressive (AR) LLMs, offering faster inference throug
arXiv:2510.01167v2 Announce Type: replace-cross Abstract: Aligning large language models to human preferences is inherently multidimensional, yet most pipelines collapse heterogeneous signals into a s
arXiv:2606.02355v1 Announce Type: new Abstract: Long-horizon LLM agents can benefit from reusable skills, yet existing skill-based methods often rely on external skill generators during training or pe
arXiv:2606.01126v1 Announce Type: cross Abstract: Pruning is a process designed to reduce the number of weights in a large neural network. This can substantially speed up inference but might cause a c
arXiv:2510.09608v2 Announce Type: replace-cross Abstract: Vision-language models (VLMs) could power real-time assistants and autonomous agents, but they face a critical challenge: understanding near-i
arXiv:2606.01086v1 Announce Type: cross Abstract: Flow and diffusion models generate high-quality samples in many modalities; however, many network evaluations are required during inference due to num
arXiv:2606.01080v1 Announce Type: cross Abstract: Large language models often improve on difficult tasks by spending inference-time compute on a reasoning trace before producing the final answer. That
arXiv:2606.01238v1 Announce Type: cross Abstract: While diffusion-based policies have impressive performance and expressivity, their long offline training slows down the data collection and policy dep
arXiv:2606.01967v1 Announce Type: new Abstract: While prompt engineering is instrumental in maximizing the capabilities of Large Language Models (LLMs) during inference, the role of prompts during tra
arXiv:2606.01243v1 Announce Type: new Abstract: Latent reasoning enables Large Language Models (LLMs) to perform multi-step inference within continuous hidden states, offering efficiency gains over ex
arXiv:2606.00735v1 Announce Type: cross Abstract: In distributed Mixture-of-Experts (MoE) inference, input-dependent token routing interacts with GPU performance variability to create persistent strag
arXiv:2510.17045v2 Announce Type: replace-cross Abstract: Video reasoning using Large Multimodal Models (LMMs) relies on costly reinforcement learning (RL) and verbose chain-of-thought, resulting in s
arXiv:2605.30625v1 Announce Type: cross Abstract: Inferring continuous probability paths from sparse snapshots is a fundamental challenge in domains like single-cell biology, where high-fidelity data
b9451 is the latest release of llama.cpp, published on June 1, 2026 . Llama.cpp is an LLM inference project implemented in C/C++ that enables efficient local execution of large language models. This r
llama.cpp b9452 is a release of the LLM inference C/C++ project from the ggml-org repository. This release likely includes updates to the software's core functionality, bug fixes, or new features that
Release b9455 is a build of llama.cpp, a C/C++ implementation for LLM inference . This release represents a specific commit or version update to the llama.cpp project, which is used for running large
Release b9464 is a version of llama.cpp, a project that enables LLM inference with minimal setup and state-of-the-art performance on a wide range of hardware. This specific release likely contains upd
arXiv:2605.31494v1 Announce Type: new Abstract: Post-training of language models is commonly framed as a sample-score-update loop implemented by gradient descent. A recent line of work, exemplified by
arXiv:2605.30550v1 Announce Type: new Abstract: Adaptive systems often need to make task-specific decisions about people from limited evidence: a tutor may need to anticipate how a learner will approa
arXiv:2605.30753v1 Announce Type: new Abstract: Diffusion-based large language models (dLLMs) support parallel text generation via iterative denoising, yet inference remains latency-heavy because many
arXiv:2603.23398v2 Announce Type: replace-cross Abstract: Generative modeling of discrete data, such as graphs, underpins many scientific and industrial applications, including molecular discovery and
Processing millions of user reviews in real-time, under strict latency and cost constraints, is no easy task. Trustpilot has been doing exactly that with custom machine learning since long before larg
arXiv:2510.15614v3 Announce Type: replace Abstract: Many scientific problems are underdetermined: multiple distinct hypotheses are equally consistent with the same observations. In such settings, effe
arXiv:2602.19049v2 Announce Type: replace Abstract: Large language models increasingly rely on long chains of thought to improve accuracy, yet such gains come with substantial inference-time costs. We
arXiv:2605.30462v1 Announce Type: cross Abstract: Can a dataset be recognized from the spurious correlations it induces during training? We argue that datasets leave dataset-specific traces in a model
arXiv:2605.31057v1 Announce Type: new Abstract: Dense self-attention is the compute and quality bottleneck of long-video diffusion inference: cost grows quadratically with the sequence length, and bey
Make sure to join our live Spaces chat on MiniMax M3 starting in 4 hours. You can pre-submit questions by replying to this tweet. MiniMax M3 is live and Together AI is powering its inference 🚀 Tomorro
arXiv:2605.30736v1 Announce Type: cross Abstract: The rapid development of large language models, each with distinct capabilities and inference costs, raises a practical deployment question: given an
arXiv:2602.07721v3 Announce Type: replace-cross Abstract: KV-cache retrieval is essential for long-context LLM inference, yet existing methods struggle with distribution drift and high latency at scal
arXiv:2605.30503v1 Announce Type: new Abstract: Learning to reach arbitrary goals from sparse feedback requires agents to infer a rich notion of reachability across state--goal pairs. Goal-conditioned
arXiv:2605.30855v1 Announce Type: new Abstract: Frame-wise action-controlled image-to-video generation is a promising paradigm for interactive world simulation, where each control signal should elicit
arXiv:2605.30580v1 Announce Type: new Abstract: Speculative decoding has become a crucial component of large language model (LLM) inference, enabling faster generation by drafting multiple tokens and
arXiv:2605.30852v1 Announce Type: new Abstract: Speculative Decoding (SD) accelerates low-concurrency LLM inference by employing a draft-then-verify paradigm. However, mainstream methods typically rel
arXiv:2605.31457v1 Announce Type: new Abstract: With the rapid advancement of large multimodal models (LMMs), inference-time overhead has become a key bottleneck for real-world deployment. Existing me
arXiv:2605.31466v1 Announce Type: new Abstract: Reconstructing the complete geometry of a scene from a single RGB image remains challenging - especially when inferring hidden structures where visual e