All entries

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

What's Changed x/create: quantize lm_head at 8-bit in the requested family by @jessegross in #17357 test: harden flaky updater and transfer unit tests by @dhiltgen in #17378 server: fix ps data race o

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

What's Changed mlx update by @dhiltgen in #17332 model/parsers: finalize incomplete GLM tool calls by @dhiltgen in #17250 docs: update retirements by @mxyng in #17289 model: align Laguna with upstream

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

Copilot now bills usage at listed API rates. Compare direct model access with the coding workflow, policy, and harness work around it. The post Copilot vs. raw API access: What are you actually paying

What's Changed launch: keep Claude Code channels available by @hoyyeva in #17210 cmd: remove dead agent prompt wrappers by @ParthSareen in #17227 agent: reorder working directory instruction by @Parth

Canvases turn AI into interactive workspaces where you can visualize information, explore workflows, and take action across complex tasks. The post How to build interactive experiences with canvases a

The **v0.32.2‑rc1** release (commit 4d1b53e, signed with a GPG key) introduces server-side logic to detect download stalls that occur before any data is received. It also removes the stall‑timeout set

This refactors the existing integration tests into 3 priumary groups: fast, release, and library. It also refines some of the release tests to drop some of the older models and pick up newer models, w

**Release v0.32.2‑rc0 (commit de1ce45)** adds support for Compute Capability 10.0 in the Linux “CUDA v12” preset, enabling B200‑class GPUs to use the `cuda_v12` backend even when drivers do not meet t

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

What's Changed Improved Gemma 4 tool calling and multi-turn reasoning, including more reliable tool-response continuations Fixed a recurrent MLX model cache leak that could increase memory use across

[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

What's Changed New interactive agent experience: running ollama now launches an agent to help you code and delegate work ❯ ollama Ollama 0.32.0 ▸ Chat, Code, & Work (glm-5.2:cloud) Chat with models, c

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

How migrating Copilot code review to shared Unix-style code exploration tools reduced review cost by reshaping agent workflows around pull request evidence. The post Better tools made Copilot code rev

The search results do not contain specific information about v0.32.0-rc0. Based on the version numbering and context from Ollama's release patterns, v0.32.0-rc0 is a release candidate for Ollama, a la

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