CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-15 11:17:31 +00:00
Code Issues Packages Projects Releases Wiki Activity

readme : add RVV,ZVFH,ZFH,ZICBOP support for RISC-V (#17259)

Browse Source 
Signed-off-by: Wang Yang <yangwang@iscas.ac.cn>
This commit is contained in:
ixgbe
2025-11-14 15:12:56 +08:00
committed by GitHub
parent f1bad23f88
commit 307772fcda
2 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.github/copilot-instructions.md vendored
View File

@@ -9,7 +9,7 @@ llama.cpp is a large-scale C/C++ project for efficient LLM (Large Language Model
- **Size**: ~200k+ lines of code across 1000+ files - **Size**: ~200k+ lines of code across 1000+ files
- **Architecture**: Modular design with main library (`libllama`) and 40+ executable tools/examples - **Architecture**: Modular design with main library (`libllama`) and 40+ executable tools/examples
- **Core dependency**: ggml tensor library (vendored in `ggml/` directory) - **Core dependency**: ggml tensor library (vendored in `ggml/` directory)
- **Backends supported**: CPU (AVX/NEON optimized), CUDA, Metal, Vulkan, SYCL, ROCm, MUSA - **Backends supported**: CPU (AVX/NEON/RVV optimized), CUDA, Metal, Vulkan, SYCL, ROCm, MUSA
- **License**: MIT - **License**: MIT
## Build Instructions ## Build Instructions

1
README.md
View File

@@ -61,6 +61,7 @@ range of hardware - locally and in the cloud.
- Plain C/C++ implementation without any dependencies - Plain C/C++ implementation without any dependencies
- Apple silicon is a first-class citizen - optimized via ARM NEON, Accelerate and Metal frameworks - Apple silicon is a first-class citizen - optimized via ARM NEON, Accelerate and Metal frameworks
- AVX, AVX2, AVX512 and AMX support for x86 architectures - AVX, AVX2, AVX512 and AMX support for x86 architectures
- RVV, ZVFH, ZFH and ZICBOP 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 - 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) - 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 - Vulkan and SYCL backend support