Knowledge catalogue
arXiv:2603.16621v2 Announce Type: replace Abstract: We propose a conjugate and calibrated Gaussian process (GP) model for multi-class classification by exploiting the geometry of the probability simpl
arXiv:2606.20419v2 Announce Type: replace Abstract: Vision-language models (VLMs) often generate fluent but visually unsupported descriptions, especially by mentioning objects absent from the image. W
arXiv:2608.28229v1 Announce Type: cross Abstract: Grammar-constrained decoding helps large language models produce syntactically valid structured outputs, such as code, JSON, and SQL. For context-free
arXiv:2608.27843v1 Announce Type: new Abstract: Contemporary language models can converse fluently and influence human decisions, yet their exchanges do not enter a continuing, vulnerable life of thei
arXiv:2608.27871v1 Announce Type: new Abstract: Long-video understanding remains challenging for Multimodal Large Language Models (MLLMs) due to limited context length. Uniform sampling may miss cruci
Kirsten Korosec / TechCrunch: The Pentagon launches ChatGPT Mil and Grok for Government on its GenAI.mil platform, giving its 3M personnel access to AI tools “tailored to warfighter needs” — The Penta
arXiv:2608.27885v1 Announce Type: new Abstract: Multimodality translation (e.g., text-to-image) is a core generative AI task. However, existing approaches (1) follow generative paths that do not direc
arXiv:2608.27540v1 Announce Type: cross Abstract: We develop a mathematical theory of superposition in neural networks using tools from frame theory and compressed sensing. In our model, a sparse bina
arXiv:2608.28216v1 Announce Type: new Abstract: Locating a specific object instance in a cluttered scene using a single reference image and a short description, and reporting when that instance is abs
With b10726, the default --lazy-mode change keeps the 51B-parameter PLE n-gram embedding table of Qwen 3.8 Flash Next on disk: it is mmap'd and its rows are read on demand during inference, even with
Together AI, in partnership with greptile, announces its AI‑powered code‑review platform that is trusted by more than 11,000 teams for reviewing pull requests within the full context of their codebase
arXiv:2608.27879v1 Announce Type: new Abstract: Articulated human pose provides detailed body-configuration information beyond coarse spatial relationships, but whether this detail yields greater disc
Hi All, I am currently contemplating an upgrade from my 5060ti 16gb. I am getting ~40t/s with 130k context on Qwen 3.8 IQ3_S HF quant. I am running llama.cpp on linux. Objective is to increase context
metal : add fa-vec tunings for M2 (#27940) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/43902029 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silic
ggml: allow passing alloc dependencies in graph_optimize (#27301) ggml: allow passing alloc dependencies in graph_optimize add alloc dep tests add TODO about using flat array Website: https://llama.ap
memory : copy Hadamard matrix to k_rot tensor only if it has buffer assigned to prevent crashes during context shift of unquantized K cache (#27967) Co-authored-by: Stanisław Szymczyk sszymczy@gmail.c
metal : fix null-pipeline crash for F16 src1 mul_mat/mul_mat_id (#25648) metal : fail closed on mul_mat shapes with missing F16 kernels metal : abort on nil pipeline in encoder_set_pipeline metal : ad
sycl: split long rows in TOP_K instead of one work-group per row (#27847) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/43958406 macOS/iOS: macOS Apple Si
hexagon: support for device discovery and create sessions on demand (#27785) hex-devices: add support for lazy session allocation and cleanup dev interfaces Co-authored-by: Marco Colombo mcolombo@qti.
rpc : fix pre-rdma macOS versions (#27815) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/43962220 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silic
vendor : update cpp-httplib to 0.54.0 (#27919) vendor : update cpp-httplib to 0.54.0 vendor : update cpp-httplib to 0.54.0 and 0.54.1 Website: https://llama.app Attestations: https://github.com/ggml-o
metal : Add fa-vec tuning for M3 Pro (#27963) Related issue: #27668 Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/43966636 macOS/iOS: macOS Apple Silicon
metal: add fa-vec tunings for M3 Ultra (#27999) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/43968762 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple
rpc: fix apple rdma error spew on teardown (#27908) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/43970664 macOS/iOS: macOS Apple Silicon (arm64) macOS Ap
ggml : add ggml_backend_op_alloc_size_may_expand, use it in RPC (#27960) some backends (Metal, SYCL, WebGPU) require additional memory for fleeting data for certain ops, which is reflected in their ge
common: rename --tensor-read-lazy to --lazy-mode, add -lzm shorthand (#27969) Rename the --tensor-read-lazy CLI argument to --lazy-mode, to match the internal lazy_mode parameter, and add a -lzm short
hip : optimize Q2_0 dot-product path for gfx1201 (#26753) hip/gfx1201: optimize q2_0 vec_dot_q2_0_q8_1 with native amdgcn perm Broadened HIP's Q2_0 perm optimization Remove redundant HIP perm availabi
hip: tune rdna 3 mmq config (#26284) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/44012223 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (ar
CUDA: use the fast mm_ids_helper path for any n_expert_used (#27978) The optimized path grouped warp lanes by token and required warp_size % n_expert_used == 0, with a single hardcoded exception paddi
llama: improve TENSOR_READ_LAZY handling (#27837) force lazy tensor on cpu if lazy is on llama: improve TENSOR_READ_LAZY handling Website: https://llama.app Attestations: https://github.com/ggml-org/l
Banger paper from Stanford on efficient test-time scaling. If you run agents that think for a long time, this one is worth your time. (bookmark it) Long reasoning keeps the entire trace in memory thro
Leo @Synthwavedd 🚨 SCOOP: Astra recently graduated from the dogfood stage, and is now being made available to select OpenAI partners under the name 'ultima-alpha' If feedback over this weekend is posi
I’ve been experimenting with MiniMax H3 and finally have video generation working in TensorSharp. TensorSharp started primarily as a local GGUF/LLM inference engine, so getting a video-generation pipe
I DON’T THINK PEOPLE REALIZE HOW MASSIVE THIS IS YET @HuggingFace and @PollenRobotics just released Microduck. It is a new legged robot for 399. It passed 1 million in sales in under SEVEN hours 🤯 The
LLMs will always be bulls in a China shop. Nailed it, December 2022. We are still suffering the consequences. And they are about to get so much worse. No wonder Silicon Valley tried for so long to dep
Running on a M1 Max 64 GB: - SSD streaming for tensors - SSD streaming for engrams - SSD streaming for MTP How is it possible? * Custom Q4 quant: benchmarked all metal tensors then picked and spliced
If you own 4xR9700 and were waiting for the model to make them shine, then I have some good news for you! It's running at 80-120 tokens/second for generation and 12k token/second prefill for a single
@claudedevs: Anthropic will “permanently” raise weekly Claude Code limits by 25% on Sept. 14 for most plans, which will work out a 17% reduction, given the current 50% boost — Starting September 14, w
vulkan: Change mul_mat_id to pad K rather than N (#27925) The N padding is needed for mul_mat, but not mul_mat_id. For mul_mat_id, we indirect the row index through a shared memory lookup table which
metal : add fa-vec tunings for M1 Max (#27932) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/43859747 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple S
vulkan: combine duplicated fastdiv functions, rename the one optimizing small divs (#27526) vulkan: combine duplicated fastdiv functions, rename the one optimizing small divs remove one more fastdiv W
sycl: make --fit respect --fit-target better (#27629) improve the --fit algorithm to take into account the actual peak required VRAM for a given context size on a SYCL backend. This includes both prop
metal : add remaining fa-vec tunings for M4 Pro (#27915) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/43865923 macOS/iOS: macOS Apple Silicon (arm64) mac
metal : assert shared memory padding (#27951) metal : assert shared memory padding cont : add ref Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/43867822 m
Banger paper from Apple. If you build MCP servers, this can help you turn your specification into an evaluation suite. (bookmark it) It's actually a really neat idea that's easy to implement. And it s
GLM-5.3-Flash is live on Fireworks on day… 2 Why? Because we take quality very seriously. We found a benchmark discrepancy we couldn’t explain, so we delayed the launch to investigate. Day 0 (Wed): we
Hardware: rtx 5080 16 gb vram; 64 gb ram ddr5 6000hz; ssd with unlimited memory; ryzen 7 9800 x3d. OS: Windows 11 Software: I’d prefer llama.cpp, but it’s not a strict requirement; I’ll use whatever y
People who moved from older version to this new one, how much improvements do you see on inference? Ex: llama.cpp performance? This new version comes with Linux Kernel 7.0. Hope AMD cards gonna enjoy
I kept running into the same thing. Change a system prompt, get a different answer, and I couldn't tell if that was my change or just the sampler. The loop made it worse. Edit the Modelfile in another
Tim Ingham / Music Business Worldwide: Sony Music and Warner Chappell sue Anthropic, Dario Amodei, and Benjamin Mann, alleging tens of thousands of copyrighted songs were used to train Claude's LLMs —
hi i make tool for this called llmog it's purpose to make llms free to - auto annotation datasets - reclassification existing yolo datasets running totally local using llama cpp or vllm or use externa
arXiv:2608.26164v1 Announce Type: new Abstract: Large language models can interpret natural-language chemistry questions, but their internal reasoning is difficult to inspect, constrain, and validate.
arXiv:2608.26581v1 Announce Type: new Abstract: Low-bit quantization offers a promising avenue for reducing the computational and memory demands of Multimodal Large Language Models (MLLMs). Recent har
ALL of this was avoidable. We didn’t need to torture. We didn’t need to create an illegal shadow justice system. We have an incredible federal justice system that has proven for DECADES it can ethical
arXiv:2608.26921v1 Announce Type: cross Abstract: We introduce AraMS-28k, the largest publicly released line-level dataset of genuine historical Arabic manuscripts, comprising 14 books, 3,043 pages, a
arXiv:2607.18064v2 Announce Type: replace-cross Abstract: Coding agents can now be left alone to improve software against a score. In this pattern--recently popularized as 'autoresearch'--the agent re
metal : add fa-vec tunings for M4 Pro (#27824) This is a followup contribution to efeda76 as requested in https://github.com/ggml-org/llama.cpp/discussions/27668 to add support for additional Apple GP
metal : add fa-vec tunings for M3 Max, M5 and M5 Pro (#27863) metal : add fa-vec tunings for M5 This is a followup contribution to efeda76 as requested in https://github.com/ggml-org/llama.cpp/discuss
sycl: use TILE for quantized KV decode on BMG (#26689) Route quantized KV decode to TILE on Xe2 (BMG) only, keep VEC on other archs until validated there. Website: https://llama.app Attestations: http
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