Search: “models”

sycl: contiguous fast path + 32-bit index math for unary elementwise ops (#25946) sycl: contiguous fast path + 32-bit index math for unary elementwise ops sycl: use fastdiv for elementwise index math

llama: move suppress_tokens handling to common/sampling (#26276) llama: move suppress_tokens handling to common/sampling address security issues rm has_logit_bias Website: https://llama.app macOS/iOS:

Disable -ffast-math on HIP (#25495) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux: Ub

ggml-metal: FWHT kernel for metal backend (#25924) metal fwht wip shape guard and formatting formatting Formatting and typos Co-authored-by: YiChen Lv 63285796+forforever73@users.noreply.github.com fi

ggml-cuda: add chunked SSD matmul for Mamba-2 prefill acceleration (#22675) ggml-cuda: add chunked SSD matmul for Mamba-2 prefill acceleration cuda: added SSD CICD fixes for CUDA / HIP / MUSA / MSVC.

vulkan: add iq4_nl support back to FA (#24585) vulkan: add iq4_nl support back to FA I was originally concerned about wasting shared memory on the LUT, but it's small and unlikely to matter in practic

ggml : set output of view src (#25729) llama-graph: set_outputs to t->view_src change set_output to GGML_ASSERT about views not being outputs sampler : avoid views in outputs cont : fix dist sampler c

server: abstract llama_memory calls to common_memory (#26221) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64)

opencl: skip the Adreno KQ/KQV image kernels for multi-stream batches (#26189) The Adreno KQ/KQV image1d kernels (ggml_cl_mul_mat_kq_kqv_adreno) ignore dim 3 entirely: the sub-buffer covers only nb02*

args: add -lm mlock where it mlocks but doesnt mmap (#26135) arg: add -lm mlock where it mlocks but doesnt mmap Signed-off-by: Aaron Teo aaron.teo1@ibm.com docs: rm unwanted docs changes Signed-off-by

ggml-cpu: Enable BF16 tiled gemm optimization on PowerPC (#26068) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (

tests : remove unnecessary sync in test-save-load-state (#26166) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x

ggml : adjust logic for offloading ops to weight's backend (#25832) ggml : adjust logic for offloading ops to weight's backend llama : dsv4 graph fixes Website: https://llama.app macOS/iOS: macOS Appl

sycl(build): parallelize ocloc invocations (#25903) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFra

fit : count nextn (MTP) blocks in n_gpu_layers so front layers stay on GPU (#26177) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISA

common : add common_print_available_devices() (#26170) Signed-off-by: Adrien Gallouët angt@huggingface.co Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64,

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

args: refactor mlock/mmap/directio into load-mode (#20834) args: overhaul mmap/mlock/dio into single arg Signed-off-by: Aaron Teo aaron.teo1@ibm.com docs: update docs with llama-gen-docs Signed-off-by

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

ggml: enable PowerPC backend variants on AIX (#25983) ggml: enable PowerPC backend variants on AIX Allow the PowerPC CPU backend variants to be built on AIX by extending the platform check in the CMak

Fix DeepSeek4 crafted template (#25414) chat: fix DS4 template to explicitly follow reference behavior Support DeepSeekv4 flag (drop_reasoning). fix: hook DS3.2 parser for DS4 as well fix: add tool re

hexagon: activation ops update (#25974) hex-geglu: optimized all-in-one geglu microkernel hex-geglu: enable non-contiguous src and strided DMA hex-act: enable non-contiguous srs and strided DMA for re

CUDA: Improve NVFP4 W4A4 activation quantization (#25730) Squash history before conflict-resolution during rebase on master WIP commit Add 32-byte loads, restore per-block amax Use nvfp4x4 intrinsic w

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)

mtmd : use align_corners for qwen3vl vision position embedding interpolation (#25781) The Qwen3-VL learned position embedding is interpolated to the runtime patch grid with the default bilinear+antial

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

cuda: GET_ROWS quants (#25962) cuda: add k-quant support to GET_ROWS Device-side embedding lookups require GET_ROWS to handle the k-quants used by common GGUF recipes (Q4_K_M stores token_embd as q6_K

webgpu : add CONV_2D_DW (depthwise conv2d) kernel (#25847) webgpu : add CONV_2D_DW (depthwise conv2d) kernel Implement GGML_OP_CONV_2D_DW for the WebGPU backend, ported from the Vulkan backend's conv2

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

opencl: disable FA and MoE weights repack to work around compiler issues for Adreno 850 GPU (#25745) opencl: workaround for A850 compiler compat opencl: fix DX compiler version parsing and cleanup Co-

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

llama.cpp is an open-source software library that performs inference on various large language models , and b9934 represents a specific build release in the project's continuous versioning system. The

b9908 is a build-tagged release from llama.cpp , the open-source C/C++ inference engine for large language models. llama.cpp is an open-source software library that performs inference on various large

B9932 is a continuous build-tagged release from the llama.cpp project , an open-source C/C++ inference engine for running large language models locally. llama.cpp performs inference on various large l

Build b9839 of llama.cpp adds offline mode support to the llama download command for checking cached models without network access, and fixes a use-after-free bug in the URL-task callback. llama.cpp i

B9832 is a build release of llama.cpp from the ggml-org project , which is a free and open-source tool that allows you to run AI models locally on Windows, Linux and macOS . The release likely contain

b9825 is a release of llama.cpp, the C/C++ implementation for large language model inference . This build represents an intermediate version in the ongoing development of llama.cpp, part of the ggml-o

b9810 is a release build of llama.cpp, an open-source software library that performs inference on various large language models such as Llama. The build identifier follows the project's versioning sch

B9816 is a release build number for llama.cpp, an open-source project that enables efficient large language model inference in C/C++ on consumer hardware. This release likely contains bug fixes, perfo

Release b9585 of llama.cpp fixes granite speech model inference by applying embedding scale when deepstack is not used . The release was published on June 9, 2026, and represents a bug fix within the

Release b9548 of llama.cpp includes a spec fix for vocabulary compatibility checking , addressing issues related to model format validation. This build provides compiled binaries for multiple platform

Release b9549 of llama.cpp adds support for the Gemma4 MTP model architecture . The release includes pre-built binaries for multiple platforms including macOS, Linux, Android, and Windows with various