Instructions to use replicate/paged-attention with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Kernels
How to use replicate/paged-attention 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/paged-attention", version=1) - Notebooks
- Google Colab
- Kaggle
Uploaded using `kernel-builder`.
Browse files- build/torch210-cxx11-cu126-aarch64-linux/_ops.py +3 -3
- build/torch210-cxx11-cu126-aarch64-linux/{_paged_attention_cuda_83cf4a3.abi3.so → _paged_attention_cuda_0278991.abi3.so} +1 -1
- build/torch210-cxx11-cu128-aarch64-linux/_ops.py +3 -3
- build/torch210-cxx11-cu128-aarch64-linux/{_paged_attention_cuda_83cf4a3.abi3.so → _paged_attention_cuda_0278991.abi3.so} +1 -1
- build/torch210-cxx11-cu130-aarch64-linux/_ops.py +3 -3
- build/{torch211-cxx11-cu130-aarch64-linux/_paged_attention_cuda_83cf4a3.abi3.so → torch210-cxx11-cu130-aarch64-linux/_paged_attention_cuda_0278991.abi3.so} +2 -2
- build/torch211-cxx11-cu126-aarch64-linux/_ops.py +3 -3
- build/torch211-cxx11-cu126-aarch64-linux/{_paged_attention_cuda_83cf4a3.abi3.so → _paged_attention_cuda_0278991.abi3.so} +1 -1
- build/torch211-cxx11-cu128-aarch64-linux/_ops.py +3 -3
- build/torch211-cxx11-cu128-aarch64-linux/{_paged_attention_cuda_83cf4a3.abi3.so → _paged_attention_cuda_0278991.abi3.so} +1 -1
- build/torch211-cxx11-cu130-aarch64-linux/_ops.py +3 -3
- build/{torch210-cxx11-cu130-aarch64-linux/_paged_attention_cuda_83cf4a3.abi3.so → torch211-cxx11-cu130-aarch64-linux/_paged_attention_cuda_0278991.abi3.so} +2 -2
- build/torch29-cxx11-cu129-aarch64-linux/_ops.py +3 -3
- build/torch29-cxx11-cu129-aarch64-linux/{_paged_attention_cuda_83cf4a3.abi3.so → _paged_attention_cuda_0278991.abi3.so} +1 -1
build/torch210-cxx11-cu126-aarch64-linux/_ops.py
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
import torch
|
| 2 |
-
from . import
|
| 3 |
-
ops = torch.ops.
|
| 4 |
|
| 5 |
def add_op_namespace_prefix(op_name: str):
|
| 6 |
"""
|
| 7 |
Prefix op by namespace.
|
| 8 |
"""
|
| 9 |
-
return f"
|
|
|
|
| 1 |
import torch
|
| 2 |
+
from . import _paged_attention_cuda_0278991
|
| 3 |
+
ops = torch.ops._paged_attention_cuda_0278991
|
| 4 |
|
| 5 |
def add_op_namespace_prefix(op_name: str):
|
| 6 |
"""
|
| 7 |
Prefix op by namespace.
|
| 8 |
"""
|
| 9 |
+
return f"_paged_attention_cuda_0278991::{op_name}"
|
build/torch210-cxx11-cu126-aarch64-linux/{_paged_attention_cuda_83cf4a3.abi3.so → _paged_attention_cuda_0278991.abi3.so}
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 140013424
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8e21e5b57dd79518e56b8bb80c33a618ecc81f51689735b99971c2aeb18c65a
|
| 3 |
size 140013424
|
build/torch210-cxx11-cu128-aarch64-linux/_ops.py
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
import torch
|
| 2 |
-
from . import
|
| 3 |
-
ops = torch.ops.
|
| 4 |
|
| 5 |
def add_op_namespace_prefix(op_name: str):
|
| 6 |
"""
|
| 7 |
Prefix op by namespace.
|
| 8 |
"""
|
| 9 |
-
return f"
|
|
|
|
| 1 |
import torch
|
| 2 |
+
from . import _paged_attention_cuda_0278991
|
| 3 |
+
ops = torch.ops._paged_attention_cuda_0278991
|
| 4 |
|
| 5 |
def add_op_namespace_prefix(op_name: str):
|
| 6 |
"""
|
| 7 |
Prefix op by namespace.
|
| 8 |
"""
|
| 9 |
+
return f"_paged_attention_cuda_0278991::{op_name}"
|
build/torch210-cxx11-cu128-aarch64-linux/{_paged_attention_cuda_83cf4a3.abi3.so → _paged_attention_cuda_0278991.abi3.so}
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 167603936
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:39293b814992eef82eda225fd2e3c63aa1e0ea1ef4f2887b348b96e6a4f6a957
|
| 3 |
size 167603936
|
build/torch210-cxx11-cu130-aarch64-linux/_ops.py
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
import torch
|
| 2 |
-
from . import
|
| 3 |
-
ops = torch.ops.
|
| 4 |
|
| 5 |
def add_op_namespace_prefix(op_name: str):
|
| 6 |
"""
|
| 7 |
Prefix op by namespace.
|
| 8 |
"""
|
| 9 |
-
return f"
|
|
|
|
| 1 |
import torch
|
| 2 |
+
from . import _paged_attention_cuda_0278991
|
| 3 |
+
ops = torch.ops._paged_attention_cuda_0278991
|
| 4 |
|
| 5 |
def add_op_namespace_prefix(op_name: str):
|
| 6 |
"""
|
| 7 |
Prefix op by namespace.
|
| 8 |
"""
|
| 9 |
+
return f"_paged_attention_cuda_0278991::{op_name}"
|
build/{torch211-cxx11-cu130-aarch64-linux/_paged_attention_cuda_83cf4a3.abi3.so → torch210-cxx11-cu130-aarch64-linux/_paged_attention_cuda_0278991.abi3.so}
RENAMED
|
@@ -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 sha256:58edf8df21a3c46f397b1d42fc56f6a9d25a45c2dd96752440524dcee296d6b5
|
| 3 |
+
size 86069336
|
build/torch211-cxx11-cu126-aarch64-linux/_ops.py
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
import torch
|
| 2 |
-
from . import
|
| 3 |
-
ops = torch.ops.
|
| 4 |
|
| 5 |
def add_op_namespace_prefix(op_name: str):
|
| 6 |
"""
|
| 7 |
Prefix op by namespace.
|
| 8 |
"""
|
| 9 |
-
return f"
|
|
|
|
| 1 |
import torch
|
| 2 |
+
from . import _paged_attention_cuda_0278991
|
| 3 |
+
ops = torch.ops._paged_attention_cuda_0278991
|
| 4 |
|
| 5 |
def add_op_namespace_prefix(op_name: str):
|
| 6 |
"""
|
| 7 |
Prefix op by namespace.
|
| 8 |
"""
|
| 9 |
+
return f"_paged_attention_cuda_0278991::{op_name}"
|
build/torch211-cxx11-cu126-aarch64-linux/{_paged_attention_cuda_83cf4a3.abi3.so → _paged_attention_cuda_0278991.abi3.so}
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 140009304
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:488ca223b03ad675658d665ff07e92ba63b681a042d496e9b1b7a7a909a79945
|
| 3 |
size 140009304
|
build/torch211-cxx11-cu128-aarch64-linux/_ops.py
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
import torch
|
| 2 |
-
from . import
|
| 3 |
-
ops = torch.ops.
|
| 4 |
|
| 5 |
def add_op_namespace_prefix(op_name: str):
|
| 6 |
"""
|
| 7 |
Prefix op by namespace.
|
| 8 |
"""
|
| 9 |
-
return f"
|
|
|
|
| 1 |
import torch
|
| 2 |
+
from . import _paged_attention_cuda_0278991
|
| 3 |
+
ops = torch.ops._paged_attention_cuda_0278991
|
| 4 |
|
| 5 |
def add_op_namespace_prefix(op_name: str):
|
| 6 |
"""
|
| 7 |
Prefix op by namespace.
|
| 8 |
"""
|
| 9 |
+
return f"_paged_attention_cuda_0278991::{op_name}"
|
build/torch211-cxx11-cu128-aarch64-linux/{_paged_attention_cuda_83cf4a3.abi3.so → _paged_attention_cuda_0278991.abi3.so}
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 167599784
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d60ef9232dc6b362b500d509a48455ebacfe76bf4593e93238035fb9b4d93a4a
|
| 3 |
size 167599784
|
build/torch211-cxx11-cu130-aarch64-linux/_ops.py
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
import torch
|
| 2 |
-
from . import
|
| 3 |
-
ops = torch.ops.
|
| 4 |
|
| 5 |
def add_op_namespace_prefix(op_name: str):
|
| 6 |
"""
|
| 7 |
Prefix op by namespace.
|
| 8 |
"""
|
| 9 |
-
return f"
|
|
|
|
| 1 |
import torch
|
| 2 |
+
from . import _paged_attention_cuda_0278991
|
| 3 |
+
ops = torch.ops._paged_attention_cuda_0278991
|
| 4 |
|
| 5 |
def add_op_namespace_prefix(op_name: str):
|
| 6 |
"""
|
| 7 |
Prefix op by namespace.
|
| 8 |
"""
|
| 9 |
+
return f"_paged_attention_cuda_0278991::{op_name}"
|
build/{torch210-cxx11-cu130-aarch64-linux/_paged_attention_cuda_83cf4a3.abi3.so → torch211-cxx11-cu130-aarch64-linux/_paged_attention_cuda_0278991.abi3.so}
RENAMED
|
@@ -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:d00fd53a3a42aeb16fd5131db9c29b43a3052001f92a416867c214067f436666
|
| 3 |
+
size 86065184
|
build/torch29-cxx11-cu129-aarch64-linux/_ops.py
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
import torch
|
| 2 |
-
from . import
|
| 3 |
-
ops = torch.ops.
|
| 4 |
|
| 5 |
def add_op_namespace_prefix(op_name: str):
|
| 6 |
"""
|
| 7 |
Prefix op by namespace.
|
| 8 |
"""
|
| 9 |
-
return f"
|
|
|
|
| 1 |
import torch
|
| 2 |
+
from . import _paged_attention_cuda_0278991
|
| 3 |
+
ops = torch.ops._paged_attention_cuda_0278991
|
| 4 |
|
| 5 |
def add_op_namespace_prefix(op_name: str):
|
| 6 |
"""
|
| 7 |
Prefix op by namespace.
|
| 8 |
"""
|
| 9 |
+
return f"_paged_attention_cuda_0278991::{op_name}"
|
build/torch29-cxx11-cu129-aarch64-linux/{_paged_attention_cuda_83cf4a3.abi3.so → _paged_attention_cuda_0278991.abi3.so}
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 181953688
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:229bec87299f02e8fc345bd873b80ffa165dda7a4bf26f50793dd3716824ef1d
|
| 3 |
size 181953688
|