mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-09-07 20:47:30 +02:00
ggerganov
c3148ebe38
Performance work on the MPP tensor API flash attention kernel (NBLK == 2 branch, i.e. dv > 128, e.g. 256/256 prefill). The QK^T + softmax was already hoisted out of the d-block loop (previous commit); this closes the remaining gap to the vec kernel: - C = 32 kv items per chunk (was 64): the smaller K/V operand and P tiles fit registers better. The pad buffer is written with matching 32-wide chunks when the tensor path is active (the reserved pad space is 64-wide, a superset of what the vec kernel needs). - online softmax with ONE GLOBAL running max (scalar) instead of per-row maxes: the max cancels in O/S, so any constant >= max score seen so far is valid; a global max makes the per-chunk O rescale a uniform scalar multiply with no per-element index decode. The rescale also does not overlap the tensor core (it serializes between QK^T and PV), so it is skipped entirely when the max did not change (alpha == 1) - with random or causal scores the max stabilizes after a few chunks. - softmax state in per-thread registers (M, S[QPSG], alpha, lmax/lsum), no shared memory or simdgroup barriers in this branch. - sinks correction uses the final global max (O and S are both relative to it); this also removes the per-row max tracking. Measured on Apple M5 Max (256/256, nq=512, f16 K/V, mask, paired A/B): kv=20000: vec 25.05 ms, tensor 23.60 ms (1.06x) kv=10000: vec 8.48 ms, tensor 8.10 ms (1.05x) (previously ~0.71-0.73x before the hoisting, ~0.82-0.84x after) test-backend-ops -o FLASH_ATTN_EXT: 4809/4809 pass with the tensor path enabled and disabled. Note: 16 queries per threadgroup is 2x faster in isolated microbenchmarks (K/V-bandwidth bound per query) but spills in the full kernel and is ~30% slower; 8 queries stays the sweet spot (documented in the kernel).
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
|
|
|
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 [In Progress] | 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
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.cpprepo and merge PRs into themasterbranch - 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