Tag
A pull request to llama.cpp adds Nemotron 3.5 Transcribe support in the mtmd (multimodal) module, extending the library's audio transcription capabilities.
A pull request to llama.cpp adds support for the Clover GPU/accelerator backend, extending the library's hardware compatibility for LLM inference.
llama.cpp 合入 PR #30928，新增 FlintForCausalLM 模型架构支持，由 alexey-rsi 提交。
ggerganov 在 llama.cpp 仓库提交 PR #30459，为 common 新增 --spec-draft-n-ubatch 选项，用于调整推测解码的 draft micro-batch 大小。
A pull request to llama.cpp adds inference support for the MiniCPM-V 4.7 multimodal vision-language model, extending the C/C++ LLM inference framework's model coverage.
vLLM 合并了对 `/v1/systemone` 的支持，作为其开源 LLM 推理与服务库的最新功能更新。
A pull request to llama.cpp adds support for the K2 Horizon dense model and MoVA architecture, extending local LLM inference coverage in the popular C/C++ inference framework.
llama.cpp 的 PR #26610 由 am17an 提交，为 RPC 后端新增 `-sm tensor`（tensor split）选项，使张量可在多设备 RPC 服务器间分配。
CodeCrab 是一款基于 Tauri 的本地优先桌面应用，利用本地 CLI 在数秒内完成 Pull Request 审查，代码完全在本机处理，100% 客户端，不会离开用户机器。
A user shares their setup for free, simple web search extraction in Open WebUI using OpenSERP, including two PRs: one making OpenSERP compatible with OWUI's extractor and another adding OpenSERP as a search provider in Open WebUI.
A pull request to ggml-org/llama.cpp adds inference support for the GLM-5.3-Flash (GLM5-Next) model, extending the library's coverage of Zhipu AI's GLM family.
This pull request fuses a chain of operations in the Vulkan backend for the qwen4exp model to optimize inference performance in llama.cpp.
DeepSeek-V4.1-Flash AI model was used on NVIDIA DGX Spark units to automatically perform kernel work, read project documents, and open a pull request, showcasing real AI automation in software development.
A pull request adds support for the NVIDIA Nemotron-3-Puzzle-75B-A9B model in the llama.cpp inference tool.
This article reports recent bug fixes and updates in llama.cpp for the Qwen Flash Next model, advising users to update their builds frequently.
Support for DFlash2 has been merged into llama.cpp via pull request #27342, adding local convolution and candidate selector features to the LLM inference tool.
Devin, an AI tool, now provides video receipts for app testing by generating test plans, executing user flows, and delivering annotated recordings to visually verify work.
Introducing Tastelint, an AI agent that runs on every pull request to provide design feedback, aiming to bridge the automation gap in product design compared to code development.
A pull request (PR#27210) for adaptive MTP has been submitted to llama.cpp, a C/C++ implementation for LLM inference with minimal setup and high performance.
An npm package that automates feedback handling in apps by opening pull requests through a cloud agent.