日本語のみで絞り込む
This repository provides a ready-to-use container image with the llama.cpp server server compiled with Vulkan support and without AVX requirement to run on old ...
2024/11/26 -Run the following command to compile the project: docker build -t llama-cpp-vulkan -f .devops/llama-server-vulkan.Dockerfile . 4. Create a ...
2025/9/27 -Running LLMS with llama.cpp using vulkan · Building vulkan enabled llama.cpp (using docker) · First try – small LLM · Second try – bigger LLM.
2026/9/17 -There are four ways to install llama.cpp: the llama.app script, which drops a 15 MB llama binary into ~/.local/bin; Homebrew; ...
2025/9/20 -Story: When llama.cpp-vulkan (either built by myself or pulled from ghcr.io) couldn't find my 4060Ti, docker.io/nvidia/vulkan:1.3-470 can find ...
2026/7/15 -I got around 50 tokens / s from llama-server logs. Follow your benchmark command, I only get 40 tokens. Any clues? docker run -it --gpus=all -v ...
This is an automated build project providing Docker images tailored for AMD platforms (ROCm and Vulkan) for llama.cpp . Features. Extremely Lightweight: ...
2025/8/4 -Software Stack: llama.cpp + Vulkan. llama.cpp is a lightweight C++ implementation of the LLaMA architecture that allows you to run LLMs directly ...
2026/6/11 -The ggml Vulkan backend specifically fails to enumerate physical devices. Workaround: pin to ghcr.io/ggml-org/llama.cpp:server-vulkan-b9426 .
2025/1/31 -llama.cpp already supports Vulkan. This is where all the hard work is at. Ollama hardly does anything on top of it to support Vulkan. You just ...