Instructions to use replicate/mamba-ssm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Kernels
How to use replicate/mamba-ssm with Kernels:
# !pip install kernels from kernels import get_kernel # a version (or an explicit revision) is required; see the "Files and versions" tab for the available ones kernel = get_kernel("replicate/mamba-ssm", version=1) - Notebooks
- Google Colab
- Kaggle
Use default compute capabilities
Browse files- build.toml +0 -1
build.toml
CHANGED
|
@@ -8,7 +8,6 @@ src = [
|
|
| 8 |
]
|
| 9 |
|
| 10 |
[kernel.selective_scan]
|
| 11 |
-
cuda-capabilities = [ "7.0", "7.2", "7.5", "8.0", "8.6", "8.7", "8.9", "9.0" ]
|
| 12 |
src = [
|
| 13 |
"selective-scan/reverse_scan.cuh",
|
| 14 |
"selective-scan/selective_scan.cpp",
|
|
|
|
| 8 |
]
|
| 9 |
|
| 10 |
[kernel.selective_scan]
|
|
|
|
| 11 |
src = [
|
| 12 |
"selective-scan/reverse_scan.cuh",
|
| 13 |
"selective-scan/selective_scan.cpp",
|