Instructions to use replicate/flash-attn3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Kernels
How to use replicate/flash-attn3 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/flash-attn3", version=1) - Notebooks
- Google Colab
- Kaggle
Build uploaded using `kernels`.
Browse files
build/torch29-cxx11-cu128-x86_64-linux/_flash_attn3_37baf3f_dirty.abi3.so
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d918c767f0bf857244f61e505783441c1ec44d3a6b315f90dd235735d3b277e8
|
| 3 |
+
size 804184680
|
build/torch29-cxx11-cu130-x86_64-linux/_flash_attn3_37baf3f_dirty.abi3.so
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1448c6f7afcecbaa97f0265a41948cb4ce27cd3990790d5eb3042c6445ae8e2f
|
| 3 |
+
size 823692904
|