README: add graphic for matrix multiplication (#6881)

This commit is contained in:
Johannes Gäßler 2024-04-24 21:29:13 +02:00 committed by GitHub
parent b4e4b8a935
commit 784e11dea1
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 1241 additions and 1 deletions

View File

@ -1117,7 +1117,9 @@ docker run --gpus all -v /path/to/models:/models local/llama.cpp:server-cuda -m
- Clean-up any trailing whitespaces, use 4 spaces for indentation, brackets on the same line, `void * ptr`, `int & a` - Clean-up any trailing whitespaces, use 4 spaces for indentation, brackets on the same line, `void * ptr`, `int & a`
- See [good first issues](https://github.com/ggerganov/llama.cpp/issues?q=is%3Aissue+is%3Aopen+label%3A%22good+first+issue%22) for tasks suitable for first contributions - See [good first issues](https://github.com/ggerganov/llama.cpp/issues?q=is%3Aissue+is%3Aopen+label%3A%22good+first+issue%22) for tasks suitable for first contributions
- Tensors store data in row-major order. We refer to dimension 0 as columns, 1 as rows, 2 as matrices - Tensors store data in row-major order. We refer to dimension 0 as columns, 1 as rows, 2 as matrices
- Matrix multiplication is unconventional: [`z = ggml_mul_mat(ctx, x, y)`](https://github.com/ggerganov/llama.cpp/blob/880e352277fc017df4d5794f0c21c44e1eae2b84/ggml.h#L1058-L1064) means `zT = x @ yT` - Matrix multiplication is unconventional: [`C = ggml_mul_mat(ctx, A, B)`](https://github.com/ggerganov/llama.cpp/blob/880e352277fc017df4d5794f0c21c44e1eae2b84/ggml.h#L1058-L1064) means $C^T = A B^T \Leftrightarrow C = B A^T.$
![matmul](media/matmul.png)
### Docs ### Docs

BIN
media/matmul.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 260 KiB

1238
media/matmul.svg Normal file

File diff suppressed because it is too large Load Diff

After

Width:  |  Height:  |  Size: 51 KiB