All entries

**Ollama v0.32.13 Release (14 Aug)** The release contains a single signed commit (ID 0f25c31) verified with GitHub’s GPG key B5690EEEBB952194. The primary change in this version is the addition of dev

ggml : fix arm builds, unused var (#26991) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Li

ggml-hip : remove -funsafe-math-optimizations (#26696) It enables -fassociative-math, which reassociates FP reductions and can flip greedy argmax on RDNA3.5 (e.g. MTP speculative decode diverging from

sycl : Add DMMV ESIMD Q3_K kernel (#26251) Add DMMV Q4_K and Q6_K ESIMD kernels Configure cmake build with -DGGML_SYCL_ESIMD=ON to enable. Signed-off-by: Todd Malsbary todd.malsbary@intel.com Refactor

sycl: remove separate fp32 type promotion in gemm non-oneDNN path (#26372) sycl: use automatic fp16 promotion in gemm sycl: remove redundant comment Website: https://llama.app macOS/iOS: macOS Apple S

ggml-cpu/ops: vectorize flash-attention V-cache F16 to F32 conversion (#26947) Co-authored-by: jinzihao jinzihao.jzh@alibaba-inc.com Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) m

spec: enable backend sampling for both dflash & dspark (#26958) dflash: enable backend sampling for both dflash & dspark enable p_min > 0 in backend sampling and add guard cont : add TODO Co-authored-

common : auto-detect spec type from draft GGUF metadata (#26814) common : auto-detect spec type from draft GGUF metadata When -md loads a local draft model without --spec-type, the sidecar inference i

metal : add TQ2_0 support (#26980) metal: add TQ2_0 support Add support for the GGML_TYPE_TQ2_0 (ternary, 2 bits per element) type in the Metal backend. Assisted-by: llama.cpp:DeepSeek-v4-Flash-0731 c

spec : auto-detect mtp draft model type (#27005) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramew

server : serve index.html with no-cache (#27006) index.html was served with max-age=31536000, immutable like the hashed assets, but its name is stable while its contents change every build, so a cache

chat : fix LFM2 tool call arg name prefix ambiguity (#26960) Assisted-by: Claude Opus 5 Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled)

[SYCL] Support host pinned mem to improve SYCL Host-to-Device Memory Access (#26789) support host pinned mem, ggml_backend_sycl_host_buffer_type_get_max_size, fix the thread-safe issue Website: https:

OpenVINO: Qwen3.5, memory optimization, and test-recurrent-state-rollback (#26952) OpenVINO backend: 1) enable gpt-oss moe on OV bk; 2) enable mxfp4 support OpenVINO backend: disable TOPK_MOE op test

common: apply CPU parameters across tools (#27026) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFram

mtmd: support pocket-tts (#26871) adapt the api text model ok working impl, need verify and clean up mtmd: build the pocket-tts transposed convolutions as GEMM + col2im ggml_conv_transpose_1d has no g

imatrix.cpp: Move finite check and only check touched experts (#26861) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS In

chat : tighten bare function parsing for Qwen models (#26793) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64)

common: Add CLI > ENV > models-presets > INI precedence CLI flags have the highest precedence ENV vars have the second-highest precedence System and User configs have the lowest precedence Linux/BSD/M

What's Changed Models that don't set a repeat_penalty now default to 1.0 (off) instead of 1.1, matching other engines and speeding up speculative decoding; set a per-model parameter if an older model

ModelOpt checkpoints apply a float32 global scale to every projection output on top of the per-group quantization scales. Running the multiply and the cast back to the activation dtype as separate eag

Learn how to write your first prompt in the GitHub Copilot app, choose the right context and model, and start your first task with confidence. The post Write your first prompt with the GitHub Copilot

ci : target ROCm 7.14 for build and release (#25775) Switch ROCm from 7.2.1 to 7.14 ROCm 7.14 is the first production release using TheRock build system. It can be installed using multi-arch deliverab

opencl: transpose the K tile in local memory for FA prefill kernels (#26428) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED ma

Address review comment of PR 25532 (#26852) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework L

ggml-webgpu: fix CI errors from #25025 and #25262 (#26566) test new flash_attn test rebase and fix to disable subgrou matrices when max_kv_tile == 0 delete log output Add i32 support to cpy and enable

common/peg : suppress incomplete escape sequences (#26780) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iO

model : fix SWA not being enabled for EXAONE 4.5 (#26848) model : fix SWA not being enabled for EXAONE 4.5 load_arch_hparams tests hparams.n_layer() == 64 before LLM_KV_NEXTN_PREDICT_LAYERS has been r

Muse Glimmer Muse Glimmer is now available on all platforms. Muse Glimmer can power coding agent applications such as Claude Code, Codex, Pi and more, as well as long-running personal assistants such

NVIDIA Nemotron 3.5 Lightning NVIDIA Nemotron 3.5 Lightning is an open 30B mixture-of-experts (MoE) model with 3B active parameters built for that execution layer of always-on agents. It is designed f

ggml-webgpu : refactor several wgsl files and simplify flash_attn wgsl. (#26134) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLE

model-saver : fix expert shared/chunk FFN length key clobber (#26693) The saver called add_kv with LLM_KV_EXPERT_SHARED_FEED_FORWARD_LENGTH twice, the second time passing n_ff_chexp. gguf_set_val_u32

model : Granite-Switch Architecture (#25107) granite-switch: add llama.cpp backend (POC, CPU) New 'granite-switch' architecture: a dense, all-attention Granite-4.1 model with N embedded LoRA adapters

vendor : update cpp-httplib to 0.53.0 (#26821) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramewor

model: add MTP support for Nemotron model (#26725) model: add MTP support for Nemotron Nano model model: add mtp_flags for nemotron model address review comments Website: https://llama.app macOS/iOS:

ggml : require contiguous src for ROLL on CUDA and Metal (#25928) ggml_roll only asserts nb[0] == ggml_type_size, so a permuted src is a valid input, but the CUDA and Metal roll kernels index by ne al

ggml-cpu : fix CPU affinity mask being ignored on Android (#26838) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel

llama : support multi-output backend sampling (#25532) Enable backend sampling with token speculation Clamp the mask sum before converting it into the sampled index Add a numeric context parameter dec

Enterprise Java developers have a new superpower—drive GitHub Copilot from idiomatic Java code with annotations, virtual threads, and more. The post Using the GitHub Copilot SDK for Java appeared firs

Muse Glimmer Note: Muse Glimmer is currently available via initial support via Ollama's MLX engine on Apple Silicon. Additional support and optimizations for Apple Silicon, NVIDIA, AMD, and other plat

v0.32.8 is an Oct 10, 2023 release of the ollama repository on GitHub, following a pre‑release tag v0.32.8‑rc0. The update adds Muse Glimmer support for NVIDIA, AMD and additional platforms, with the

ci: rm GGML_HIP_ROCWMMA_FATTN (#26760) Signed-off-by: Aaron Teo aaron.teo1@ibm.com Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISAB

ggml-cpu : fix missing Q5_0 dispatch in SpaceMiT backend (#26792) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (

CUDA: fix thread/block count in quantized cpy kernel launches (#26731) CUDA: fix thread/block count in quantized cpy kernel launches tests: add uneven block count cpy case Website: https://llama.app m

server: add initial tool isolation support (via docker) (#26507) server: add initial tool isolation support (via docker) add docs adapt get_info py: fix type check cont separate tools_io_sandbox / too

server, ui: only offer a working directory when a tool reads it (#26762) The working directory chip showed up as soon as the server exposed any builtin tool, so a server started with just get_datetime