b10165
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
Knowledge catalogue
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*
ggml-webgpu: Fix some binding alias issues to support all archs, fix recurrent-state-rollback test (#25931) Add overlap glu variant to support all archs, fix recurrent-state-rollback test format Fix a
model: Add Laguna-S-2.1 LLM_TYPE (#26233) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Lin
mtmd: Add Vision Support for Minimax-M3 (#25113) Add preliminary MiniMax-M3 support Text-only port that re-uses existing components: MiniMax-M2 style GQA with per-head QK-norm and partial rotary, Deep
server + ui: fix stream routes for model names containing a slash (#26137) server + ui: refactor resumable stream routes to query string conv_id The conversation id can embed a model name containing s
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 (
common: fix explicit -md precedence over draft sidecar resolution (#26165) common: fix explicit -md precedence over draft sidecar resolution Follow-up of #25955, an explicit --model-draft file given w
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
model: Add support for Nanbeige4.2 (#25994) support nanbeige4.2 model fix fix flake8 Lint check fix loop bound check and drop redundant head_dim Co-authored-by: root lizongqiang@kanzhun.com Website: h
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: support MiMo-V2.5 audio input (RVQ-based model) (#26190) gguf converter for mimo audio fix conv cpp impl nits nits 2 Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple
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
common: infer the speculative type from the draft repo sidecars (#25989) With -hfd pointing to a repo that ships mtp-/dflash-/eagle3- sidecars and no --spec-type given, the draft resolved to a full mo
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
[SYCL] Flash Attention with XMX engine via oneDNN (#25222) [SYCL] F16 (default) Flash Attention with XMX engine via oneDNN graph API; Qwen3.6-27b-Q8_0 prefill speed up x1.21 at p=512 and x4.26 at p=80
sycl: Increase minimum buffer size for USM system allocations (#25525) Raise the threshold for minimum buffer size from 1 GiB to 4 GiB, based on real-world experiments of overcommitting device memory
DeepseekV4: reduce graph splits (#25702) macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux: Ubuntu x64 (CPU) Ubuntu
server : refactor prompt cache state ownership (#25649) server : clear checkpoints upon prompt clear server : move the prompt state data to the server_prompt_cache Assisted-by: pi:llama.cpp/Qwen3.6-27
The search did not return the specific details of the b9947 release. Based on the repository and context available: B9947 is a release of llama.cpp, which enables LLM inference in C/C++ . The release
b9948 is a build release of llama.cpp, an open-source C/C++ project for efficient large language model inference. The project ships continuous build-tagged releases using a build numbering system rath
b9949 is a release build of llama.cpp, the open-source C/C++ inference engine for running large language models locally. llama.cpp releases are published frequently with build versions in the b-series
b9950 is a release of llama.cpp, a C/C++ tool for LLM inference . This build number represents one of the frequent incremental releases from the llama.cpp project, which follows a rapid development cy
Release b9956 is a build version of llama.cpp, an open-source project for LLM inference in C/C++ . The project releases frequently, with multiple releases published in a single day , and b9956 represe
Release b9967 of llama.cpp, an LLM inference project in C/C++, includes an update to the server component allowing it to accept null sampling parameters (PR #25538). This change enables more flexible
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
b9935 is a build release from the llama.cpp project, which implements LLM inference in C/C++. The project doesn't follow traditional release practices, as multiple releases can be published in a singl
llama.cpp b9936 is a continuous build-tagged release from the open-source llama.cpp project , which is an open-source C/C++ inference engine that powers most of the local-AI ecosystem . This release c
The search results do not contain specific details about release b9938. However, based on the context available, b9938 is one of the regular build releases from the llama.cpp project. Llama.cpp releas
Release b9940 of llama.cpp was published on July 9, 2026 , and includes changes related to llama-bench initialization parameters . The release provides pre-built binaries across multiple platforms inc
b9945 is a build-tagged release of llama.cpp, an open-source library that performs inference on large language models and is co-developed alongside the GGML tensor library. The llama.cpp project does
The search results show that b9946 is a specific release build tag from the llama.cpp project, though the exact details of that particular build are not visible in the page content retrieved. Based on
Based on the available information, b9905 is a build-tagged release from the llama.cpp project, which is an open-source C/C++ inference engine that powers most of the local-AI ecosystem . The project
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
llama.cpp is an open-source software library that performs inference on various large language models , and the project ships continuous build-tagged releases rather than traditional semantic versioni
Based on available information, b9910 is a release tag from the llama.cpp project, an open-source C/C++ implementation for running large language model inference locally on consumer hardware. Llama.cp
b9913 is a build-tagged release from llama.cpp, an open-source software library that performs inference on various large language models. The project does not use traditional semantic versions; instea