Hugging Face's logo

Kernels:
flashrt
/
fp8-kv-attention

Kernel card Files
xet
 Community
liangsu9988 commited on
Commit
42b7493
·
verified ·
1 Parent(s): e9e70c0

Uploaded using `kernel-builder`.

Browse files
Files changed (12) hide show
  1. build/torch211-cxx11-cu128-x86_64-linux/{_fp8_kv_attention_cuda_b52bebd.abi3.so → _fp8_kv_attention_cuda_1798e7f.abi3.so} +1 -1
  2. build/torch211-cxx11-cu128-x86_64-linux/_ops.py +3 -3
  3. build/torch211-cxx11-cu128-x86_64-linux/metadata.json +3 -3
  4. build/torch211-cxx11-cu130-x86_64-linux/{_fp8_kv_attention_cuda_b52bebd.abi3.so → _fp8_kv_attention_cuda_1798e7f.abi3.so} +1 -1
  5. build/torch211-cxx11-cu130-x86_64-linux/_ops.py +3 -3
  6. build/torch211-cxx11-cu130-x86_64-linux/metadata.json +3 -3
  7. build/torch212-cxx11-cu130-x86_64-linux/{_fp8_kv_attention_cuda_b52bebd.abi3.so → _fp8_kv_attention_cuda_1798e7f.abi3.so} +1 -1
  8. build/torch212-cxx11-cu130-x86_64-linux/_ops.py +3 -3
  9. build/torch212-cxx11-cu130-x86_64-linux/metadata.json +3 -3
  10. build/torch212-cxx11-cu132-x86_64-linux/{_fp8_kv_attention_cuda_b52bebd.abi3.so → _fp8_kv_attention_cuda_1798e7f.abi3.so} +1 -1
  11. build/torch212-cxx11-cu132-x86_64-linux/_ops.py +3 -3
  12. build/torch212-cxx11-cu132-x86_64-linux/metadata.json +3 -3
build/torch211-cxx11-cu128-x86_64-linux/{_fp8_kv_attention_cuda_b52bebd.abi3.so → _fp8_kv_attention_cuda_1798e7f.abi3.so} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e3e0c4c76e13d15337f89ee4cb8fb6c74523c86fe91443baf09a8f5310543c3e
3
  size 288176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf401a2268d87ffe836d824c39fb3286fa12828eba64a5e3c27e61845556fcd3
3
  size 288176
build/torch211-cxx11-cu128-x86_64-linux/_ops.py CHANGED
@@ -1,9 +1,9 @@
1
  import torch
2
- from . import _fp8_kv_attention_cuda_b52bebd
3
- ops = torch.ops._fp8_kv_attention_cuda_b52bebd
4
 
5
  def add_op_namespace_prefix(op_name: str):
6
  """
7
  Prefix op by namespace.
8
  """
9
- return f"_fp8_kv_attention_cuda_b52bebd::{op_name}"
 
1
  import torch
2
+ from . import _fp8_kv_attention_cuda_1798e7f
3
+ ops = torch.ops._fp8_kv_attention_cuda_1798e7f
4
 
5
  def add_op_namespace_prefix(op_name: str):
6
  """
7
  Prefix op by namespace.
8
  """
9
+ return f"_fp8_kv_attention_cuda_1798e7f::{op_name}"
build/torch211-cxx11-cu128-x86_64-linux/metadata.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "name": "fp8-kv-attention",
3
- "id": "_fp8_kv_attention_cuda_b52bebd",
4
  "version": 1,
5
  "license": "Apache-2.0",
6
  "python-depends": [],
@@ -14,8 +14,8 @@
14
  "algorithm": "sha256",
15
  "files": {
16
  "__init__.py": "AipNkYPvsd/zyT+YU7bggBObENJYocXbAV7/Yr5A+6c=",
17
- "_fp8_kv_attention_cuda_b52bebd.abi3.so": "4+DEx24T0VM3+J7ky4+2x0UjyG/pFEO68JqPUxBUPD4=",
18
- "_ops.py": "fyBj4qCb8mz0wmxfXUOJbmL9Qt/z363aB9xuZOoskjE=",
19
  "fp8_kv_attention/__init__.py": "DFYPlrhXwYjEqCl/8n0SmWGZV8NFml5DPhMjKfv98GY="
20
  }
21
  }
 
1
  {
2
  "name": "fp8-kv-attention",
3
+ "id": "_fp8_kv_attention_cuda_1798e7f",
4
  "version": 1,
5
  "license": "Apache-2.0",
6
  "python-depends": [],
 
14
  "algorithm": "sha256",
15
  "files": {
16
  "__init__.py": "AipNkYPvsd/zyT+YU7bggBObENJYocXbAV7/Yr5A+6c=",
17
+ "_fp8_kv_attention_cuda_1798e7f.abi3.so": "z0AaImjYf/6DbYJMOfsyhvoSgo66ZKXjwn5hhFVW/NM=",
18
+ "_ops.py": "u1tuL5lFum0BIgl8+j1z86OkjJn3e4Mnmc/29zQSfHA=",
19
  "fp8_kv_attention/__init__.py": "DFYPlrhXwYjEqCl/8n0SmWGZV8NFml5DPhMjKfv98GY="
20
  }
21
  }
build/torch211-cxx11-cu130-x86_64-linux/{_fp8_kv_attention_cuda_b52bebd.abi3.so → _fp8_kv_attention_cuda_1798e7f.abi3.so} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:22805a5e3a18daedec22122a1599919a183e977e6b939d49d0571101d8daf9bf
3
  size 289032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee536f2f46f5118d095c14a22ebbf275811a39c3aba56b774a1c6797c234044a
3
  size 289032
build/torch211-cxx11-cu130-x86_64-linux/_ops.py CHANGED
@@ -1,9 +1,9 @@
1
  import torch
2
- from . import _fp8_kv_attention_cuda_b52bebd
3
- ops = torch.ops._fp8_kv_attention_cuda_b52bebd
4
 
5
  def add_op_namespace_prefix(op_name: str):
6
  """
7
  Prefix op by namespace.
8
  """
9
- return f"_fp8_kv_attention_cuda_b52bebd::{op_name}"
 
1
  import torch
2
+ from . import _fp8_kv_attention_cuda_1798e7f
3
+ ops = torch.ops._fp8_kv_attention_cuda_1798e7f
4
 
5
  def add_op_namespace_prefix(op_name: str):
6
  """
7
  Prefix op by namespace.
8
  """
9
+ return f"_fp8_kv_attention_cuda_1798e7f::{op_name}"
build/torch211-cxx11-cu130-x86_64-linux/metadata.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "name": "fp8-kv-attention",
3
- "id": "_fp8_kv_attention_cuda_b52bebd",
4
  "version": 1,
5
  "license": "Apache-2.0",
6
  "python-depends": [],
@@ -14,8 +14,8 @@
14
  "algorithm": "sha256",
15
  "files": {
16
  "__init__.py": "AipNkYPvsd/zyT+YU7bggBObENJYocXbAV7/Yr5A+6c=",
17
- "_fp8_kv_attention_cuda_b52bebd.abi3.so": "IoBaXjoY2u3sIhIqFZmRmhg+l35rk51J0FcRAdja+b8=",
18
- "_ops.py": "fyBj4qCb8mz0wmxfXUOJbmL9Qt/z363aB9xuZOoskjE=",
19
  "fp8_kv_attention/__init__.py": "DFYPlrhXwYjEqCl/8n0SmWGZV8NFml5DPhMjKfv98GY="
20
  }
21
  }
 
1
  {
2
  "name": "fp8-kv-attention",
3
+ "id": "_fp8_kv_attention_cuda_1798e7f",
4
  "version": 1,
5
  "license": "Apache-2.0",
6
  "python-depends": [],
 
14
  "algorithm": "sha256",
15
  "files": {
16
  "__init__.py": "AipNkYPvsd/zyT+YU7bggBObENJYocXbAV7/Yr5A+6c=",
17
+ "_fp8_kv_attention_cuda_1798e7f.abi3.so": "7lNvL0b1EY0JXBSiLrvydYEaOcOrpWt3Shxnl8I0BEo=",
18
+ "_ops.py": "u1tuL5lFum0BIgl8+j1z86OkjJn3e4Mnmc/29zQSfHA=",
19
  "fp8_kv_attention/__init__.py": "DFYPlrhXwYjEqCl/8n0SmWGZV8NFml5DPhMjKfv98GY="
20
  }
21
  }
build/torch212-cxx11-cu130-x86_64-linux/{_fp8_kv_attention_cuda_b52bebd.abi3.so → _fp8_kv_attention_cuda_1798e7f.abi3.so} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:db178d36fee556c48b986da3b318c0087daf1bb0903f39fb5838ea9a326d5c10
3
  size 304040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f3555f239dbbc144b463c9a90f991f82abdb31838e360236697c859b45e1cc0
3
  size 304040
build/torch212-cxx11-cu130-x86_64-linux/_ops.py CHANGED
@@ -1,9 +1,9 @@
1
  import torch
2
- from . import _fp8_kv_attention_cuda_b52bebd
3
- ops = torch.ops._fp8_kv_attention_cuda_b52bebd
4
 
5
  def add_op_namespace_prefix(op_name: str):
6
  """
7
  Prefix op by namespace.
8
  """
9
- return f"_fp8_kv_attention_cuda_b52bebd::{op_name}"
 
1
  import torch
2
+ from . import _fp8_kv_attention_cuda_1798e7f
3
+ ops = torch.ops._fp8_kv_attention_cuda_1798e7f
4
 
5
  def add_op_namespace_prefix(op_name: str):
6
  """
7
  Prefix op by namespace.
8
  """
9
+ return f"_fp8_kv_attention_cuda_1798e7f::{op_name}"
build/torch212-cxx11-cu130-x86_64-linux/metadata.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "name": "fp8-kv-attention",
3
- "id": "_fp8_kv_attention_cuda_b52bebd",
4
  "version": 1,
5
  "license": "Apache-2.0",
6
  "python-depends": [],
@@ -14,8 +14,8 @@
14
  "algorithm": "sha256",
15
  "files": {
16
  "__init__.py": "AipNkYPvsd/zyT+YU7bggBObENJYocXbAV7/Yr5A+6c=",
17
- "_fp8_kv_attention_cuda_b52bebd.abi3.so": "2xeNNv7lVsSLmG2jsxjACH2vG7CQPzn7WDjqmjJtXBA=",
18
- "_ops.py": "fyBj4qCb8mz0wmxfXUOJbmL9Qt/z363aB9xuZOoskjE=",
19
  "fp8_kv_attention/__init__.py": "DFYPlrhXwYjEqCl/8n0SmWGZV8NFml5DPhMjKfv98GY="
20
  }
21
  }
 
1
  {
2
  "name": "fp8-kv-attention",
3
+ "id": "_fp8_kv_attention_cuda_1798e7f",
4
  "version": 1,
5
  "license": "Apache-2.0",
6
  "python-depends": [],
 
14
  "algorithm": "sha256",
15
  "files": {
16
  "__init__.py": "AipNkYPvsd/zyT+YU7bggBObENJYocXbAV7/Yr5A+6c=",
17
+ "_fp8_kv_attention_cuda_1798e7f.abi3.so": "fzVV8jnbvBRLRjyakPmR+Cq9sxg442AjZpfIWbReHMA=",
18
+ "_ops.py": "u1tuL5lFum0BIgl8+j1z86OkjJn3e4Mnmc/29zQSfHA=",
19
  "fp8_kv_attention/__init__.py": "DFYPlrhXwYjEqCl/8n0SmWGZV8NFml5DPhMjKfv98GY="
20
  }
21
  }
build/torch212-cxx11-cu132-x86_64-linux/{_fp8_kv_attention_cuda_b52bebd.abi3.so → _fp8_kv_attention_cuda_1798e7f.abi3.so} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4405b475839aaf53504639360217d40c30ebe8c4aee525617ccd1a854ca00828
3
  size 304040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7e4715f54563584e19ef3c507f7ddd7d0ed3297e28b7dba2fd1f9bcacb68051
3
  size 304040
build/torch212-cxx11-cu132-x86_64-linux/_ops.py CHANGED
@@ -1,9 +1,9 @@
1
  import torch
2
- from . import _fp8_kv_attention_cuda_b52bebd
3
- ops = torch.ops._fp8_kv_attention_cuda_b52bebd
4
 
5
  def add_op_namespace_prefix(op_name: str):
6
  """
7
  Prefix op by namespace.
8
  """
9
- return f"_fp8_kv_attention_cuda_b52bebd::{op_name}"
 
1
  import torch
2
+ from . import _fp8_kv_attention_cuda_1798e7f
3
+ ops = torch.ops._fp8_kv_attention_cuda_1798e7f
4
 
5
  def add_op_namespace_prefix(op_name: str):
6
  """
7
  Prefix op by namespace.
8
  """
9
+ return f"_fp8_kv_attention_cuda_1798e7f::{op_name}"
build/torch212-cxx11-cu132-x86_64-linux/metadata.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "name": "fp8-kv-attention",
3
- "id": "_fp8_kv_attention_cuda_b52bebd",
4
  "version": 1,
5
  "license": "Apache-2.0",
6
  "python-depends": [],
@@ -14,8 +14,8 @@
14
  "algorithm": "sha256",
15
  "files": {
16
  "__init__.py": "AipNkYPvsd/zyT+YU7bggBObENJYocXbAV7/Yr5A+6c=",
17
- "_fp8_kv_attention_cuda_b52bebd.abi3.so": "RAW0dYOar1NQRjk2AhfUDDDr6MSu5SVhfM0ahUygCCg=",
18
- "_ops.py": "fyBj4qCb8mz0wmxfXUOJbmL9Qt/z363aB9xuZOoskjE=",
19
  "fp8_kv_attention/__init__.py": "DFYPlrhXwYjEqCl/8n0SmWGZV8NFml5DPhMjKfv98GY="
20
  }
21
  }
 
1
  {
2
  "name": "fp8-kv-attention",
3
+ "id": "_fp8_kv_attention_cuda_1798e7f",
4
  "version": 1,
5
  "license": "Apache-2.0",
6
  "python-depends": [],
 
14
  "algorithm": "sha256",
15
  "files": {
16
  "__init__.py": "AipNkYPvsd/zyT+YU7bggBObENJYocXbAV7/Yr5A+6c=",
17
+ "_fp8_kv_attention_cuda_1798e7f.abi3.so": "x+RxX1RWNYThnvPFB/fd19DtMpfii326L9H5vKy2gFE=",
18
+ "_ops.py": "u1tuL5lFum0BIgl8+j1z86OkjJn3e4Mnmc/29zQSfHA=",
19
  "fp8_kv_attention/__init__.py": "DFYPlrhXwYjEqCl/8n0SmWGZV8NFml5DPhMjKfv98GY="
20
  }
21
  }