2時間前 -LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on GitHub.
2026/8/17 -llama.cpp version v0.1.0 has been released ... llama.cpp is apparently moving to semantic versioning instead of just sequential build numbers (like b10456).
2日前 -llama.cpp makes it possible to run multi-modal LLMs across a wide range of hardware - from consumer-grade local machines to high-end enterprise servers.
6日前 -llama.cpp began development in March 2023 by Georgi Gerganov as an implementation of the Llama inference code in pure C/C++ with no dependencies. This improved ...
2日前 -Today's release marks the first major version of llama.cpp and ggml. We have created a strong foundation for the future of local AI.
2026/10/6 -Changelog since v1.9.4. d1be6fd whisper : bump version to 1.9.5 (#4102) 4afec37 talk-llama : update llama.cpp to v0.6.0
2026/9/30 -Simple Python bindings for @ggerganov's llama.cpp library. This package provides: Low-level access to C API via ctypes interface. High-level Python API for ...
2026/4/9 -Llama.cpp is a C/C++ library for running LLM inference on CPUs and GPUs with quantized GGUF models, ggml backends such as CUDA and Metal, and tools like ...
2026/7/31 -Latest commit. ggerganov · readme : refresh (#26280) ... binaryTarget( name: "LlamaFramework", url: "https://github.com/ggml-org/llama.cpp/releases ...
2026/10/27 -New release ggml-org/llama.cpp version b11890 on GitHub ... UI. Check out latest releases or releases around ggml-org/llama.cpp b11890.