Search: “llm”

models : consolidate nextn row cropping into shared helpers (#30017) mimo2 : always emit h_nextn the other nextn-capable models set it unconditionally Assisted-by: pi:llama.cpp/MiMo-V2.6-Flash-MOPD mo

vocab : implement PLaMo-3 tokenizer pre-segmentation (#30045) vocab : implement PLaMo-3 tokenizer pre-segmentation The PLaMo-3 tokenizer inserts hard boundaries before running the Unigram DP, around <

context : do not re-reserve the scheduler when toggling causal_attn (#28751) context : do not re-reserve the scheduler when toggling causal_attn llama_context::set_causal_attn() marks the scheduler to

The decode loop releases MLX's pool of freed buffers every 256 generated tokens, which is also how often the KV cache grows and drops its previous, smaller buffers. The check fires only when the token

OpenVINO: optimize stateful decode and GPU MoE inference (#28638) exclude GPU/NPU failing POOL_2D case Fix pool case ggml-openvino: fix stateful decode for Gemma-4 per-layer-type head sizes ggml-openv

llama : add --n-cpu-ffn option (#26622) common : dedupe --n-cpu-moe / --spec-draft-n-cpu-moe override loops common : add --n-cpu-ffn to CPU-offload dense FFN weights of first N layers common : general

metal : fix NORM/RMS_NORM for row lengths that leave a partial simdgroup (#26708) ggml_metal_op_norm sized the threadgroup with nth = std::min(nth, args.ne00_t), which can leave nth not a multiple of

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

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

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

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

b9933 is a continuous build-tagged release of llama.cpp , the C/C++ inference engine for running large language models locally. This release represents an incremental update in llama.cpp's development

Release b9892 is a version identifier for llama.cpp, an open-source C/C++ framework for running large language model inference on consumer hardware. This specific build (b9892) represents a snapshot o

The search results don't contain specific details about release b9871. Based on the pattern evident in the search results and the context, here's the summary: B9871 is a release of llama.cpp, an open-

Release b9852 is a build version of llama.cpp, a C/C++ implementation that enables large language model inference with minimal setup and state-of-the-art performance across diverse hardware platforms

Based on the available search results, the specific release details for b9857 are not fully accessible, but this entry refers to a build release from the llama.cpp project. llama.cpp is a port of Face

Release b9858 is a continuous build-tagged release of llama.cpp , the open-source C/C++ project that enables large language model inference with minimal setup and optimized performance across diverse

Release b9850 is a version of llama.cpp, an open-source software library for large language model inference developed alongside the GGML tensor library. This release likely includes updates, bug fixes

Release b9831 of llama.cpp includes backend detection improvements and synchronization enhancements, particularly for async CUDA copies and Vulkan backend operations. Llama.cpp is designed to enable L

The search results show information about other llama.cpp releases and the project generally, but do not contain specific details about release b9824. Based on the available information about llama.cp

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

The search results do not contain specific information about the b9777 release. Based on the available information about llama.cpp releases, b9777 is an intermediate build release from the llama.cpp p

The search results do not contain specific details about the b9769 release. Based on the available information about llama.cpp and its release patterns, here is a knowledge base entry: Release b9769 o

Release b9773 of llama.cpp adds Vulkan support for the GET_ROWS_BACK operation . The release includes pre-built binaries for multiple platforms including macOS, Linux, Windows, and Android with variou

The search results did not provide specific information about the b9564 release. Based on the context of llama.cpp releases and the pattern observed with nearby releases (b9542, b9543, b9544, etc.), I

The search did not return specific details about the b9547 release. Based on the repository context and release naming convention, b9547 is a build number for llama.cpp, an open-source C/C++ implement

B9544 is an intermediate build release of llama.cpp, an open-source C/C++ library for running large language model inference. Llama.cpp uses the GGUF model format and supports multiple hardware backen

Release b9528 of llama.cpp was published on June 5, 2026. This build includes a UI update to run npm install when package-lock.json is newer than node_modules, and provides pre-compiled binaries for m

The search did not return specific details about the b9535 release. Based on the available information, b9535 is an intermediate build version from the llama.cpp project, which is a C/C++ implementati

The search results don't contain specific information about release b9536, but I found related information about nearby releases in the llama.cpp project. Based on the pattern visible in the search re

B9500 is a release of llama.cpp that includes a Metal backend optimization reducing reset heartbeat timing from 500ms to 5ms . The release provides compiled binaries across multiple platforms includin

The search results show general llama.cpp information and references to other recent builds (like b9484), but the specific details for b9487 were not clearly accessible. Based on the context from llam

B9466 is a build release in the llama.cpp project that includes fixes and improvements to speculative decoding functionality, specifically addressing n_outputs_max issues and extracting helper functio

B9473 is a release of llama.cpp, a C/C++ framework for large language model inference . The release represents a specific build commit from the ggml-org/llama.cpp repository. This entry likely documen

B9434 is a release build identifier from the llama.cpp project, an open-source C/C++ implementation for large language model inference. Llama.cpp releases include updates, optimizations, and bug fixes

b9437 is a llama.cpp release that adds OpenCL support for bf16 format by converting to f16 . The release is part of the llama.cpp project, which is an open-source C/C++ implementation that enables loc

The search didn't return specific details about the b9388 release. Based on the available information about llama.cpp, this is likely a commit/release entry for the llama.cpp project. Here's a summary

b9414 is a release build of llama.cpp that includes improvements to CUDA PTX version checking , which helps prevent incorrect kernel dispatch on different GPU architectures. This build also adds suppo

b9326 is a llama.cpp release tagged as 'sync: ggml' with pre-built binaries available for multiple platforms including macOS, Linux, Windows, Android, and openEuler, supporting various CPU and GPU bac

The search results show information about llama.cpp releases but don't contain specific details about build b9297. Based on the context and numbering (b9297 is a recent build after b9294), b9297 is li

Release b9255 of llama.cpp features a Hexagon HMX quantized matmul rework (#23368), including updates to debug logging, dequantization logic using HVX vectors, removal of non-pipelined quantization op

Build b9239 is a llama.cpp release that includes a fix for the --fit verbosity flag when used with --verbosity 4 . The release provides compiled binaries for multiple platforms including macOS (Apple

b9244 is an intermediate build release of llama.cpp, a C/C++ implementation framework for running large language models with GGUF format support. The release includes pre-compiled binaries for multipl

B9222 is a llama.cpp release that adds support for the TRI (Triangle) operation in the Hexagon HTP backend with HVX kernel additions . The release includes optimizations for Hexagon hardware accelerat