Search headlines, summaries and articles to connect the dots.
Optimized TOP_K performance on Hexagon backend by skipping bitonic sort for tiles whose maximum cannot surpass the k-th best value, replacing tile sort with top_k_scan() to reduce 256-float blocks using HVX max-reduce, and inserting only surviving elements into a sorted k-entry list. Supports k values from 2 to 64 and row widths over 1024 in both single-row and multi-row paths. NaN treated as -INF, ties preserve first-seen index. Eliminated scalar reads from VTCM in hex-top-k.
The update introduces the TOP_K_MASK operation for Hexagon, simplifying the kernel and eliminating redundant host configuration.
The update introduces initial support for the LIGHTNING_INDEXER operation in the Hexagon backend, including optimizations for HMX prefill, q4_0 and f32 K support, pipelined HMX paths, improved DMA pipeline with canonical double buffering, and enhanced kernel parameter alignment. It also adds options to force HMX/HVX execution paths and supports dimension collapse.
ComfyUI v0.44.0 introduces multiple new partner nodes for tools like Patina, VEED, BFL, Ideogram, Pruna, MiniMax, Topaz, Sonilo, and OpenAI, adding features such as higher resolution video upscaling, context window editing, and new models. Enhancements include support for ProRes and custom chroma subsampling in video saving, improved frontend handling with pinned versions, optimized tensor comparisons, and better VAE compute dtype control. Performance optimizations address redundant concatenations and memory management, while bug fixes resolve crashes related to VAE decoding and prefetch queue cleanup. The release also updates workflow templates, embedded documentation, and default settings, with contributions from new developers.
tests : adjust constants to reduce irrelevant warnings (#31254) **Website:** - **Attestations:** - **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b11954/llama-b11954-bin-macos-arm64.tar.gz) - macOS Apple Silicon (arm64, KleidiAI enabled) [DISABLED](https://github.com/ggml-org/llama.cpp/pull/23780) - [macOS Intel (x64)](https://github.com/ggml-org/llama.cpp/releases/download/b11954/llama-b11954-bin-macos-x64.tar.gz) - [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b11954/llama-b11954-xcframework.zip) **Linux:** - [Ubuntu x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b11954/llama-b11954-bin-ubuntu-x64.tar.gz) - [Ubuntu arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b1
chat : stop qwen3-coder reasoning and content before template separators (#30557) * chat : strip trailing whitespace from parsed reasoning and content Assisted-by: Claude Fable 5.1 * chat : stop qwen3-coder reasoning and content before template separators Assisted-by: Claude * tests : remove the Qwen parser case from the chat session tests Assisted-by: Claude * common : handle partial prefix until match at end of generation --------- Co-authored-by: Zeshawn Zahid Co-authored-by: Alde Rojas **Website:** - **Attestations:** - **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b11951/llama-b11951-bin-macos-arm64.tar.gz) - macOS Apple Silicon (arm64, KleidiAI enabled) [DISABLED](https://github.com/ggml-org/llama.cpp/pull/23780) - [macOS Intel
server : add realtime conversation and transcription on /v1/realtime (#31269) * server : add realtime conversation and transcription on /v1/realtime Co-authored-by: Xuan Son Nguyen Assisted-by: Claude Opus 5.5 * examples : default the realtime client to the server port 9931 Assisted-by: Claude Opus 5.5 * server : sample realtime responses right after their own decode Slots respond in turns on one context: sampling at the start of the next step read the logits of whichever slot decoded last, so concurrent sessions mixed their outputs. Assisted-by: Claude Opus 5.5 * move more stuff to server-realtime, making it self-contained * examples : fix the type check of the realtime client Assisted-by: Claude Opus 5.5 * examples : use the model card prompts in the realtime client Assisted-by: Claude O
model : add LiquidAI/d1-2B and LiquidAI/d1-omni-2B (#31275) * model : add LiquidAI/d1-2B and LiquidAI/d1-omni-2B Assisted-by: Claude Opus 5.5 * convert : keep the speech task templates out of the d1 GGUFs Assisted-by: Claude Opus 5.5 * small refactoring: no_batching --------- Co-authored-by: Xuan Son Nguyen **Website:** - **Attestations:** - **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b11945/llama-b11945-bin-macos-arm64.tar.gz) - macOS Apple Silicon (arm64, KleidiAI enabled) [DISABLED](https://github.com/ggml-org/llama.cpp/pull/23780) - [macOS Intel (x64)](https://github.com/ggml-org/llama.cpp/releases/download/b11945/llama-b11945-bin-macos-x64.tar.gz) - [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b119
server: expose the reasoning effort levels of the chat template (#31271) * server: expose the reasoning effort levels of the chat template The capability probe renders a user turn for each candidate level (minimal, low, medium, high, xhigh, max) and for an unknown level. A level is honored when it renders without raising and differently from the unknown level, which shows the template fallback. Levels sharing a render are aliases and the highest one is kept. The caps serialize to JSON, and chat_template_caps in /props reports the list as reasoning_effort_levels, from lowest to highest. * jinja: keep the caps free of the json dependency The caps keep reporting their flags as a map, and the effort levels stay a plain member. common_chat_templates_get_caps() builds the JSON the server reports
model : add LiquidAI/LFM3-Audio-2B and LiquidAI/LFM3-Omni-2B (#31257) * model : add LiquidAI/LFM3-Audio-2B and LiquidAI/LFM3-Omni-2B Co-authored-by: Xuan Son Nguyen Assisted-by: Claude Opus 5.5 * convert : read the LFM3-Audio config.json as released A transformers that knows lfm3_audio rewrites the config into another layout (no lfm/encoder keys). Assisted-by: Claude Opus 5.5 * mtmd : disable flash attention for the LFM3-Audio depthformer Assisted-by: Claude Opus 5.5 * tts : add a voice option for LFM3-Audio and LFM3-Omni The model card offers a female and a male voice; --tts-voice for llama-tts, "voice" for the server /tts. Assisted-by: Claude Opus 5.5 * clean up template handling * convert : detect LFM3-Audio and LFM3-Omni by model_type Assisted-by: Claude Opus 5.5 * move banned tokens -
common : support deferred tools and tool_reference content parts (#31256) * common : support deferred tools and tool_reference content parts Assisted-by: Claude Opus 5.5 * common : credit the deferred tools co-author Co-authored-by: Aldehir Rojas <765227+aldehir@users.noreply.github.com> Assisted-by: Claude Opus 5.5 * tests : fix the type check of the deferred tools test Assisted-by: Claude Opus 5.5 **Website:** - **Attestations:** - **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b11940/llama-b11940-bin-macos-arm64.tar.gz) - macOS Apple Silicon (arm64, KleidiAI enabled) [DISABLED](https://github.com/ggml-org/llama.cpp/pull/23780) - [macOS Intel (x64)](https://github.com/ggml-org/llama.cpp/releases/download/b11940/llama-b11940-bin-maco
model : add LiquidAI/LFM3-1.7B and LiquidAI/LFM3-VL-2B (#31252) * model : add LiquidAI/LFM3-1.7B and LiquidAI/LFM3-VL-2B Co-authored-by: Sigbjørn Skjæret Co-authored-by: Xuan-Son Nguyen Assisted-by: Claude Opus 5.5 * tests : set the SWA rope base of the LFM3 test model Assisted-by: Claude Opus 5.5 * llama : enable recurrent state rollback for LFM3 Assisted-by: Claude Opus 5.5 * Apply batched suggestions from code review Co-authored-by: Sigbjørn Skjæret Co-authored-by: Tarek Dakhran * gguf-py : align the lfm3vl mapping comments Assisted-by: Claude Opus 5.5 * llama : fix CRLF line endings from the review suggestions Assisted-by: Claude Opus 5.5 * tests : add the LFM3 Metal fusion baseline Assisted-by: Claude Opus 5.5 * llama : keep the LFM3-VL depthwise conv kernels in F32 when quantizing As
llama : build the k-pool sparse selection independently of the kq_mask shape (#31243) * llama : build the k-pool sparse selection independently of the kq_mask shape qwen4exp (QSA) and glm5-next pick cache cells by index and no longer read the kq_mask values, but they still shaped the selection like the dense kq_mask. Build the selection as [n_kv, n_tokens] over the cache cells instead, and split it into the streams of the K view right before the attention. This lets the dense mask change its layout (e.g. per-sequence row lists) without touching the sparse layers. * improve comment Co-authored-by: Georgi Gerganov * llama : drop the unused build_fused_top_k_mask args, review nits --------- Co-authored-by: Georgi Gerganov **Website:** - **Attestations:** - **macOS/iOS:** - [macOS Apple Silico
tests : speed up tensor data generation and model saving (#31145) * tests : speed up tensor data generation and model saving Refactor save_models to create only the model, not a llama_context, which is not needed for saving. Replace the slow std::normal_distribution draw with a splitmix64 + box-muller normal generator. Assisted-by: dsh:llama.cpp/ggml-org/DeepSeek-V4-Flash-Vision-Exp-GGUF (Mac Studio, M2 Ultra, 192GB) * tests : use a shared pool of normal draws for tensor data Generate a pool of normal draws once with std::mt19937 and std::normal_distribution, then have every tensor copy a cyclic slice of it instead of running a per-tensor box-muller. The name-keyed slice selection keeps the draw deterministic. Assisted-by: dsh:llama.cpp/ggml-org/DeepSeek-V4-Flash-Vision-Exp-GGUF (Mac Studi
mtmd-cli: Reduced scope of batch pointer (#31155) (#31165) * mtmd-cli: Reduced scope of batch pointer (#31155) * mtmd-cli: Remove CLI regression test **Website:** - **Attestations:** - **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b11932/llama-b11932-bin-macos-arm64.tar.gz) - macOS Apple Silicon (arm64, KleidiAI enabled) [DISABLED](https://github.com/ggml-org/llama.cpp/pull/23780) - [macOS Intel (x64)](https://github.com/ggml-org/llama.cpp/releases/download/b11932/llama-b11932-bin-macos-x64.tar.gz) - [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b11932/llama-b11932-xcframework.zip) **Linux:** - [Ubuntu x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b11932/llama-b11932-bin-ubuntu-x64.tar
server: add router device memory margin parameter for dynamic unloading (#21231) * server: add --models-memory-max parameter to allow dynamically unloading models when they exceed a memory size threshold estimate with to-be-loaded model size included use no_alloc to get memory requirements for model load only set model memory_mb if not previously calculated use memory margin instead of total size limit, apply to each device separately add server memory debug logging move llama_context_device_memory function to llama-ext.h fix model count exceeded check improve memory_per_device map naming improve variable naming, fix style also strip models memory margin from child processes cont : clean-up replace device memory map with buft memory map. Use llama_get_memory_breakdown extract duplicated ch
common : --model or -hf is required (#31242) Assisted-by: Codex **Website:** - **Attestations:** - **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b11929/llama-b11929-bin-macos-arm64.tar.gz) - macOS Apple Silicon (arm64, KleidiAI enabled) [DISABLED](https://github.com/ggml-org/llama.cpp/pull/23780) - [macOS Intel (x64)](https://github.com/ggml-org/llama.cpp/releases/download/b11929/llama-b11929-bin-macos-x64.tar.gz) - [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b11929/llama-b11929-xcframework.zip) **Linux:** - [Ubuntu x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b11929/llama-b11929-bin-ubuntu-x64.tar.gz) - [Ubuntu arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b1
model: Add MiniCPM-OCR-Jev (#30980) * model : add MiniCPM-OCR-Jev support The model is a Qwen3.5-VL trunk with a value head read at the last token: it scores an OCR text against an image rendered from it, it does not generate. Add the openbmb-minicpm-ocr-jev decision type, served by POST /v1/systemone. The class scores are the pooled output of the sequence, read with last pooling, so the conversion turns score.weight into cls.output and sets embedding_length_out. The checkpoint has no LM head, so text generation is rejected instead of using the output weights duplicated from the token embeddings. The task is fixed, so its prompt is entirely in the systemone template, the same way h2o-lightning keeps its default there. The processor of the checkpoint allows up to 16384 merged tokens per ima
ggml : relax scale to non-contiguous views (#31146) * ggml : relax scale to non-contiguous views SCALE requires src0 to be 1D-contiguous. Relax this to dim-0 contiguity with arbitrary row strides (ggml_is_contiguous_rows), same as the unary ops in the Metal backend. - ggml: relax the assert in ggml_scale_impl - cpu: address src0 rows through their byte strides (f32, bf16) - cuda: stride-aware kernel, fastdiv row decomposition - metal: support bf16 scale (guarded unary instantiations) - sycl: keep the gate at contiguous, the kernel is flat f32 Add view variants to test_scale. Verified on CPU, Metal and CUDA. Assisted-by: dsh:llama.cpp/ggml-org/Qwen3.8-Flash-Next-GGUF (RTX 5090 32GB, DDR5 128GB) * cuda : skip the softcap fusion on non-contiguous views The fused softcap kernel reads src and w
# [3.0.0](https://github.com/n8n-io/n8n/compare/n8n@2.45.0...n8n@3.0.0) (2026-10-27) ### Bug Fixes * Add file-type tooltip to artifact download button ([#41490](https://github.com/n8n-io/n8n/issues/41490)) ([4a74f02](https://github.com/n8n-io/n8n/commit/4a74f027e612f31098b354dd3a77b2c2ab98281c)) * **ai-builder:** Check execution:read in Assistant execution reads ([#41863](https://github.com/n8n-io/n8n/issues/41863)) ([a967486](https://github.com/n8n-io/n8n/commit/a9674866d075e989a5ce896432262c9a7dc8b0c7)) * **ai-builder:** Send Assistant model calls through the configured AI transport ([#41948](https://github.com/n8n-io/n8n/issues/41948)) ([9b63561](https://github.com/n8n-io/n8n/commit/9b63561cbb48f06d216f27be3b77722d97e4e74a)) * Allow custom OAuth2 scopes ([#41249](https://github.com/n8n-
