root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-25 02:44:36 +00:00
Code Issues Actions 9 Packages Projects Releases Wiki Activity

musa : update doc (#9856)

Browse Source 
Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>
This commit is contained in:
R0CKSTAR 2024-10-12 13:09:53 +08:00 committed by GitHub
parent 96776405a1
commit 943d20b411
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 10 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@ -31,7 +31,7 @@ variety of hardware - locally and in the cloud.
- 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 and AVX512 support for x86 architectures - AVX, AVX2 and AVX512 support for x86 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) - Custom CUDA kernels for running LLMs on NVIDIA GPUs (support for AMD GPUs via HIP and Moore Threads MTT GPUs via MUSA)
- Vulkan and SYCL backend support - Vulkan and SYCL backend support
- CPU+GPU hybrid inference to partially accelerate models larger than the total VRAM capacity - CPU+GPU hybrid inference to partially accelerate models larger than the total VRAM capacity
@ -413,7 +413,7 @@ Please refer to [Build llama.cpp locally](./docs/build.md)
| [BLAS](./docs/build.md#blas-build) | All | | [BLAS](./docs/build.md#blas-build) | All |
| [BLIS](./docs/backend/BLIS.md) | All | | [BLIS](./docs/backend/BLIS.md) | All |
| [SYCL](./docs/backend/SYCL.md) | Intel and Nvidia GPU | | [SYCL](./docs/backend/SYCL.md) | Intel and Nvidia GPU |
| [MUSA](./docs/build.md#musa) | Moore Threads GPU | | [MUSA](./docs/build.md#musa) | Moore Threads MTT GPU |
| [CUDA](./docs/build.md#cuda) | Nvidia GPU | | [CUDA](./docs/build.md#cuda) | Nvidia GPU |
| [hipBLAS](./docs/build.md#hipblas) | AMD GPU | | [hipBLAS](./docs/build.md#hipblas) | AMD GPU |
| [Vulkan](./docs/build.md#vulkan) | GPU | | [Vulkan](./docs/build.md#vulkan) | GPU |

8
docs/build.md
View File

@ -198,6 +198,8 @@ The following compilation options are also available to tweak performance:
### MUSA ### MUSA
This provides GPU acceleration using the MUSA cores of your Moore Threads MTT GPU. Make sure to have the MUSA SDK installed. You can download it from here: [MUSA SDK](https://developer.mthreads.com/sdk/download/musa).
- Using `make`: - Using `make`:
```bash ```bash
make GGML_MUSA=1 make GGML_MUSA=1
@ -209,6 +211,12 @@ The following compilation options are also available to tweak performance:
cmake --build build --config Release cmake --build build --config Release
``` ```
The environment variable [`MUSA_VISIBLE_DEVICES`](https://docs.mthreads.com/musa-sdk/musa-sdk-doc-online/programming_guide/Z%E9%99%84%E5%BD%95/) can be used to specify which GPU(s) will be used.
The environment variable `GGML_CUDA_ENABLE_UNIFIED_MEMORY=1` can be used to enable unified memory in Linux. This allows swapping to system RAM instead of crashing when the GPU VRAM is exhausted.
Most of the compilation options available for CUDA should also be available for MUSA, though they haven't been thoroughly tested yet.
### hipBLAS ### hipBLAS
This provides BLAS acceleration on HIP-supported AMD GPUs. This provides BLAS acceleration on HIP-supported AMD GPUs.