Note

This is adderek/llama.cpp, a fork of ggml-org/llama.cpp tuned for AMD Radeon RX 7900 XTX (gfx1100, RDNA3) on ROCm 7.2.4 / Linux, and tested only there. Upstream is merged in regularly. The most important changes:

KV cache compression

• TurboQuant KV cache (--cache-type-k/-v turbo2|turbo3|turbo4): 2.1-4.25 bits per value, 3.8x smaller than f16 at turbo4. Works on dense, GQA, sparse (QSA, Qwen3.8-Flash-Next), MLA and DSA attention; K and V may use different types.
• Correctness fixes on top of it: the QSA path read the cache in the wrong basis and silently answered from the wrong part of the context; GQA models with padded heads crashed.

Speed on RDNA3

• FlashAttention for turbo caches: 2.6-5.4x faster prefill at 16-64k context; decode up to 34% faster, on Ornith-35B faster than an f16 cache at long context.
• MoE models larger than VRAM: offloaded expert matmuls go to the GPU you choose (GGML_CUDA_OP_OFFLOAD_DEVICES), 2x prefill here.
• Models larger than VRAM + RAM on branch moe-tier (not yet in master): hot experts on the GPU, cold ones streamed from NVMe with O_DIRECT, 2.4 instead of 0.9 tokens/s on a 244 GB 397B model.

Server and runtime

• --reasoning auto does not enable thinking (upstream does); use --reasoning on.
• Speculative decoding parameters can be set per request; logs show wall-clock time and busy/total slots; a stall watchdog dumps backtraces (LLAMA_STALL_WATCHDOG_SECS).
• ROCm robustness: fixed a GPU fault on prompt-cache restore, a turbo decode hang and an abort under CUDA-graph capture.
• --hugepages for model weights; K2-Horizon model support.

Regression tests for every fork feature run in ctest (test-turbo-kv-*, test-fattn-turbo4, ...).

Details, measurements, environment variables and which GPUs it can run on (no turbo on Metal / Vulkan / SYCL; CUDA never built): FORK.md. Everything below is the upstream README, unchanged.

llama.cpp

LLM inference in C/C++

ggml / ops / maintainer PRs / dev stats / lib llama API / llama-server REST API

Quick start

A few options to get llama.cpp installed on your machine:

• Visit https://llama.app and follow the instructions
• Run with Docker - see our Docker documentation
• Download pre-built binaries from the releases page
• Build from source by cloning this repository - check out our build guide

Once installed:

# Download and run a model directly from Hugging Face
llama cli -hf ggml-org/Qwen3.5-0.8B-GGUF

# Launch OpenAI-compatible API server
llama serve -hf ggml-org/Qwen3.5-0.8B-GGUF

VLM session with llama cli

Built-in web UI against llama serve

Description

The main goal of llama.cpp is to enable LLM (and VLM) inference with minimal setup and state-of-the-art performance on a wide range of hardware - locally and in the cloud.

• Plain C/C++ implementation without any dependencies
• Apple silicon is a first-class citizen - optimized via ARM NEON, Accelerate and Metal frameworks
• AVX, AVX2, AVX512 and AMX support for x86 architectures
• RVV, ZVFH, ZFH, ZICBOP and ZIHINTPAUSE support for RISC-V architectures
• 1.5-bit, 2-bit, 3-bit, 4-bit, 5-bit, 6-bit, and 8-bit integer quantization for faster inference and reduced memory use
• Custom CUDA kernels for running LLMs on NVIDIA GPUs (support for AMD GPUs via HIP and Moore Threads GPUs via MUSA)
• Vulkan and SYCL backend support
• CPU+GPU hybrid inference to partially accelerate models larger than the total VRAM capacity

The llama.cpp project is build on top of the ggml library.

Supported backends

Backend	Target devices
BLAS	All
BLIS	All
CANN	Ascend NPU
CUDA	Nvidia GPU
HIP	AMD GPU
Hexagon	Snapdragon
IBM zDNN	IBM Z & LinuxONE
MUSA	Moore Threads GPU
Metal	Apple Silicon
OpenCL	Adreno GPU
OpenVINO [In Progress]	Intel CPUs, GPUs, and NPUs
RPC	All
SYCL	Intel GPU
VirtGPU	VirtGPU APIR
Vulkan	GPU
WebGPU	All
ZenDNN	AMD CPU

Documentation

Tools

• cli
• completion
• server
• GBNF grammars

Development

• How to build
• Running on Docker
• Build on Android
• Multi-GPU usage
• Performance troubleshooting
• GGML tips & tricks
• XCFramework
• Completions
• Models
• Release process

Contributing

• Contributors can open PRs
• Collaborators will be invited based on contributions
• Maintainers can push to branches in the llama.cpp repo and merge PRs into the master branch
• Any help with managing issues, PRs and projects is very appreciated!
• Read the CONTRIBUTING.md for more information

Acknowledgements

• yhirose/cpp-httplib - Single-header HTTP server, used by llama-server - MIT license
• nothings/stb - Single-header image format decoder, used by multimodal subsystem - Public domain
• nlohmann/json - Single-header JSON library, used by various tools/examples - MIT License
• mackron/miniaudio - Single-header audio format decoder, used by multimodal subsystem - Public domain
• sheredom/subprocess.h - Single-header process launching solution for C and C++ - Public domain