Hugging Face's logo

kernels-community
/
quantization

kernel
Model card Files Community
1
danieldk HF staff commited on
Commit
d62ac09
·
1 Parent(s): e3a7455

Build

Browse files
Files changed (24) hide show
  1. build/torch24-cxx11-cu118-x86_64-linux/quantization/__init__.py +2 -0
  2. build/torch24-cxx11-cu118-x86_64-linux/quantization/_quantization_0_0_1.abi3.so +2 -2
  3. build/torch24-cxx11-cu121-x86_64-linux/quantization/__init__.py +2 -0
  4. build/torch24-cxx11-cu121-x86_64-linux/quantization/_quantization_0_0_1.abi3.so +2 -2
  5. build/torch24-cxx11-cu124-x86_64-linux/quantization/__init__.py +2 -0
  6. build/torch24-cxx11-cu124-x86_64-linux/quantization/_quantization_0_0_1.abi3.so +2 -2
  7. build/torch24-cxx98-cu118-x86_64-linux/quantization/__init__.py +2 -0
  8. build/torch24-cxx98-cu118-x86_64-linux/quantization/_quantization_0_0_1.abi3.so +2 -2
  9. build/torch24-cxx98-cu121-x86_64-linux/quantization/__init__.py +2 -0
  10. build/torch24-cxx98-cu121-x86_64-linux/quantization/_quantization_0_0_1.abi3.so +2 -2
  11. build/torch24-cxx98-cu124-x86_64-linux/quantization/__init__.py +2 -0
  12. build/torch24-cxx98-cu124-x86_64-linux/quantization/_quantization_0_0_1.abi3.so +2 -2
  13. build/torch25-cxx11-cu118-x86_64-linux/quantization/__init__.py +2 -0
  14. build/torch25-cxx11-cu118-x86_64-linux/quantization/_quantization_0_0_1.abi3.so +2 -2
  15. build/torch25-cxx11-cu121-x86_64-linux/quantization/__init__.py +2 -0
  16. build/torch25-cxx11-cu121-x86_64-linux/quantization/_quantization_0_0_1.abi3.so +2 -2
  17. build/torch25-cxx11-cu124-x86_64-linux/quantization/__init__.py +2 -0
  18. build/torch25-cxx11-cu124-x86_64-linux/quantization/_quantization_0_0_1.abi3.so +2 -2
  19. build/torch25-cxx98-cu118-x86_64-linux/quantization/__init__.py +2 -0
  20. build/torch25-cxx98-cu118-x86_64-linux/quantization/_quantization_0_0_1.abi3.so +2 -2
  21. build/torch25-cxx98-cu121-x86_64-linux/quantization/__init__.py +2 -0
  22. build/torch25-cxx98-cu121-x86_64-linux/quantization/_quantization_0_0_1.abi3.so +2 -2
  23. build/torch25-cxx98-cu124-x86_64-linux/quantization/__init__.py +2 -0
  24. build/torch25-cxx98-cu124-x86_64-linux/quantization/_quantization_0_0_1.abi3.so +2 -2
build/torch24-cxx11-cu118-x86_64-linux/quantization/__init__.py CHANGED
@@ -13,6 +13,7 @@ from .marlin import (
13
  marlin_qqq_gemm,
14
  marlin_gemm,
15
  )
 
16
 
17
  __all__ = [
18
  "awq_marlin_repack",
@@ -25,6 +26,7 @@ __all__ = [
25
  "gptq_marlin_repack",
26
  "marlin_gemm",
27
  "marlin_qqq_gemm",
 
28
  "scaled_fp8_quant",
29
  "scaled_int8_quant",
30
  ]
 
13
  marlin_qqq_gemm,
14
  marlin_gemm,
15
  )
16
+ from ._ops import ops
17
 
18
  __all__ = [
19
  "awq_marlin_repack",
 
26
  "gptq_marlin_repack",
27
  "marlin_gemm",
28
  "marlin_qqq_gemm",
29
+ "ops",
30
  "scaled_fp8_quant",
31
  "scaled_int8_quant",
32
  ]
build/torch24-cxx11-cu118-x86_64-linux/quantization/_quantization_0_0_1.abi3.so CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:35967133ffbd0cac32aafc9e70f441264b1f41710f4f86d68723d2eb9a59cfe8
3
- size 85717704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2b7dbe4a5f68d853c46eab87bff39934ce9fb1695256c0d02c6f90ec7c4b257
3
+ size 87483216
build/torch24-cxx11-cu121-x86_64-linux/quantization/__init__.py CHANGED
@@ -13,6 +13,7 @@ from .marlin import (
13
  marlin_qqq_gemm,
14
  marlin_gemm,
15
  )
 
16
 
17
  __all__ = [
18
  "awq_marlin_repack",
@@ -25,6 +26,7 @@ __all__ = [
25
  "gptq_marlin_repack",
26
  "marlin_gemm",
27
  "marlin_qqq_gemm",
 
28
  "scaled_fp8_quant",
29
  "scaled_int8_quant",
30
  ]
 
13
  marlin_qqq_gemm,
14
  marlin_gemm,
15
  )
16
+ from ._ops import ops
17
 
18
  __all__ = [
19
  "awq_marlin_repack",
 
26
  "gptq_marlin_repack",
27
  "marlin_gemm",
28
  "marlin_qqq_gemm",
29
+ "ops",
30
  "scaled_fp8_quant",
31
  "scaled_int8_quant",
32
  ]
build/torch24-cxx11-cu121-x86_64-linux/quantization/_quantization_0_0_1.abi3.so CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c0abd1636906a69e8cf7d85fdfc7b99b6b4f4cc3d753431ad3d49ba674238c27
3
- size 105267936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80cc601f6714b2978b754a3a0581543042847d510cf4661a2697c04dddf31305
3
+ size 107014952
build/torch24-cxx11-cu124-x86_64-linux/quantization/__init__.py CHANGED
@@ -13,6 +13,7 @@ from .marlin import (
13
  marlin_qqq_gemm,
14
  marlin_gemm,
15
  )
 
16
 
17
  __all__ = [
18
  "awq_marlin_repack",
@@ -25,6 +26,7 @@ __all__ = [
25
  "gptq_marlin_repack",
26
  "marlin_gemm",
27
  "marlin_qqq_gemm",
 
28
  "scaled_fp8_quant",
29
  "scaled_int8_quant",
30
  ]
 
13
  marlin_qqq_gemm,
14
  marlin_gemm,
15
  )
16
+ from ._ops import ops
17
 
18
  __all__ = [
19
  "awq_marlin_repack",
 
26
  "gptq_marlin_repack",
27
  "marlin_gemm",
28
  "marlin_qqq_gemm",
29
+ "ops",
30
  "scaled_fp8_quant",
31
  "scaled_int8_quant",
32
  ]
build/torch24-cxx11-cu124-x86_64-linux/quantization/_quantization_0_0_1.abi3.so CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a458d5efc51f80028811707ee7b9fadb00f3bfc49917c8377188c286c4bd8e12
3
- size 109249352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b748bbe0790f44d995713ef86468f361aadce2da8eb0113ba43a8bf96ea2580b
3
+ size 110873680
build/torch24-cxx98-cu118-x86_64-linux/quantization/__init__.py CHANGED
@@ -13,6 +13,7 @@ from .marlin import (
13
  marlin_qqq_gemm,
14
  marlin_gemm,
15
  )
 
16
 
17
  __all__ = [
18
  "awq_marlin_repack",
@@ -25,6 +26,7 @@ __all__ = [
25
  "gptq_marlin_repack",
26
  "marlin_gemm",
27
  "marlin_qqq_gemm",
 
28
  "scaled_fp8_quant",
29
  "scaled_int8_quant",
30
  ]
 
13
  marlin_qqq_gemm,
14
  marlin_gemm,
15
  )
16
+ from ._ops import ops
17
 
18
  __all__ = [
19
  "awq_marlin_repack",
 
26
  "gptq_marlin_repack",
27
  "marlin_gemm",
28
  "marlin_qqq_gemm",
29
+ "ops",
30
  "scaled_fp8_quant",
31
  "scaled_int8_quant",
32
  ]
build/torch24-cxx98-cu118-x86_64-linux/quantization/_quantization_0_0_1.abi3.so CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:734f235fc2749269910ee4e988da205a9442edf73c0f9b3ef41fff100bc66707
3
- size 85709024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1369202bac8ef7fc82e7f94d66cd8d2b260cbc4e409f10a1b5b5e04f22131eb0
3
+ size 87453464
build/torch24-cxx98-cu121-x86_64-linux/quantization/__init__.py CHANGED
@@ -13,6 +13,7 @@ from .marlin import (
13
  marlin_qqq_gemm,
14
  marlin_gemm,
15
  )
 
16
 
17
  __all__ = [
18
  "awq_marlin_repack",
@@ -25,6 +26,7 @@ __all__ = [
25
  "gptq_marlin_repack",
26
  "marlin_gemm",
27
  "marlin_qqq_gemm",
 
28
  "scaled_fp8_quant",
29
  "scaled_int8_quant",
30
  ]
 
13
  marlin_qqq_gemm,
14
  marlin_gemm,
15
  )
16
+ from ._ops import ops
17
 
18
  __all__ = [
19
  "awq_marlin_repack",
 
26
  "gptq_marlin_repack",
27
  "marlin_gemm",
28
  "marlin_qqq_gemm",
29
+ "ops",
30
  "scaled_fp8_quant",
31
  "scaled_int8_quant",
32
  ]
build/torch24-cxx98-cu121-x86_64-linux/quantization/_quantization_0_0_1.abi3.so CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:516d2dbd3669ce8b9fd78f84413747bce207223f9987cbdb68e042c8ab3688ac
3
- size 105258480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45117d77739c22a5c65a18d6326c800c8300240b34926e3c5d8079f9d1c62619
3
+ size 107007424
build/torch24-cxx98-cu124-x86_64-linux/quantization/__init__.py CHANGED
@@ -13,6 +13,7 @@ from .marlin import (
13
  marlin_qqq_gemm,
14
  marlin_gemm,
15
  )
 
16
 
17
  __all__ = [
18
  "awq_marlin_repack",
@@ -25,6 +26,7 @@ __all__ = [
25
  "gptq_marlin_repack",
26
  "marlin_gemm",
27
  "marlin_qqq_gemm",
 
28
  "scaled_fp8_quant",
29
  "scaled_int8_quant",
30
  ]
 
13
  marlin_qqq_gemm,
14
  marlin_gemm,
15
  )
16
+ from ._ops import ops
17
 
18
  __all__ = [
19
  "awq_marlin_repack",
 
26
  "gptq_marlin_repack",
27
  "marlin_gemm",
28
  "marlin_qqq_gemm",
29
+ "ops",
30
  "scaled_fp8_quant",
31
  "scaled_int8_quant",
32
  ]
build/torch24-cxx98-cu124-x86_64-linux/quantization/_quantization_0_0_1.abi3.so CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b0840d3a079bbf070d21282020386b2fc121da9894be0fa88ffcb6680d92bf0f
3
- size 109243600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:399926eaf71ed4ec82c53f7ca5bcf90e024c2590ff44ca6af1b6f74156a6b6f2
3
+ size 110853632
build/torch25-cxx11-cu118-x86_64-linux/quantization/__init__.py CHANGED
@@ -13,6 +13,7 @@ from .marlin import (
13
  marlin_qqq_gemm,
14
  marlin_gemm,
15
  )
 
16
 
17
  __all__ = [
18
  "awq_marlin_repack",
@@ -25,6 +26,7 @@ __all__ = [
25
  "gptq_marlin_repack",
26
  "marlin_gemm",
27
  "marlin_qqq_gemm",
 
28
  "scaled_fp8_quant",
29
  "scaled_int8_quant",
30
  ]
 
13
  marlin_qqq_gemm,
14
  marlin_gemm,
15
  )
16
+ from ._ops import ops
17
 
18
  __all__ = [
19
  "awq_marlin_repack",
 
26
  "gptq_marlin_repack",
27
  "marlin_gemm",
28
  "marlin_qqq_gemm",
29
+ "ops",
30
  "scaled_fp8_quant",
31
  "scaled_int8_quant",
32
  ]
build/torch25-cxx11-cu118-x86_64-linux/quantization/_quantization_0_0_1.abi3.so CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f21a34510be03ab2a0ef92fed8db8aae8170d257922fbe6b2917a2b21b8df07
3
- size 85717704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df504168ad2d8eec02ddf328cdbbd50c436088e98c2347fd77f2c1b5fd2f1911
3
+ size 87483216
build/torch25-cxx11-cu121-x86_64-linux/quantization/__init__.py CHANGED
@@ -13,6 +13,7 @@ from .marlin import (
13
  marlin_qqq_gemm,
14
  marlin_gemm,
15
  )
 
16
 
17
  __all__ = [
18
  "awq_marlin_repack",
@@ -25,6 +26,7 @@ __all__ = [
25
  "gptq_marlin_repack",
26
  "marlin_gemm",
27
  "marlin_qqq_gemm",
 
28
  "scaled_fp8_quant",
29
  "scaled_int8_quant",
30
  ]
 
13
  marlin_qqq_gemm,
14
  marlin_gemm,
15
  )
16
+ from ._ops import ops
17
 
18
  __all__ = [
19
  "awq_marlin_repack",
 
26
  "gptq_marlin_repack",
27
  "marlin_gemm",
28
  "marlin_qqq_gemm",
29
+ "ops",
30
  "scaled_fp8_quant",
31
  "scaled_int8_quant",
32
  ]
build/torch25-cxx11-cu121-x86_64-linux/quantization/_quantization_0_0_1.abi3.so CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7451eaf399d27e0f7fbac108964d862b97b8f12a5fb6decdf9a955874aa95548
3
- size 105267936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5779959f67b0de0b155ebc37142f0e415db5daa4b45281f3837636795150ddac
3
+ size 107014952
build/torch25-cxx11-cu124-x86_64-linux/quantization/__init__.py CHANGED
@@ -13,6 +13,7 @@ from .marlin import (
13
  marlin_qqq_gemm,
14
  marlin_gemm,
15
  )
 
16
 
17
  __all__ = [
18
  "awq_marlin_repack",
@@ -25,6 +26,7 @@ __all__ = [
25
  "gptq_marlin_repack",
26
  "marlin_gemm",
27
  "marlin_qqq_gemm",
 
28
  "scaled_fp8_quant",
29
  "scaled_int8_quant",
30
  ]
 
13
  marlin_qqq_gemm,
14
  marlin_gemm,
15
  )
16
+ from ._ops import ops
17
 
18
  __all__ = [
19
  "awq_marlin_repack",
 
26
  "gptq_marlin_repack",
27
  "marlin_gemm",
28
  "marlin_qqq_gemm",
29
+ "ops",
30
  "scaled_fp8_quant",
31
  "scaled_int8_quant",
32
  ]
build/torch25-cxx11-cu124-x86_64-linux/quantization/_quantization_0_0_1.abi3.so CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f539485ab9a338fe8d1ed5de27bc9b0e6295c2c469910f0948dfa69ef629baf
3
- size 109249352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50de944be9760eeb8d97d8b06fd7e32d6ce4b5f2044aa38bd8171afe4ee3f346
3
+ size 110873680
build/torch25-cxx98-cu118-x86_64-linux/quantization/__init__.py CHANGED
@@ -13,6 +13,7 @@ from .marlin import (
13
  marlin_qqq_gemm,
14
  marlin_gemm,
15
  )
 
16
 
17
  __all__ = [
18
  "awq_marlin_repack",
@@ -25,6 +26,7 @@ __all__ = [
25
  "gptq_marlin_repack",
26
  "marlin_gemm",
27
  "marlin_qqq_gemm",
 
28
  "scaled_fp8_quant",
29
  "scaled_int8_quant",
30
  ]
 
13
  marlin_qqq_gemm,
14
  marlin_gemm,
15
  )
16
+ from ._ops import ops
17
 
18
  __all__ = [
19
  "awq_marlin_repack",
 
26
  "gptq_marlin_repack",
27
  "marlin_gemm",
28
  "marlin_qqq_gemm",
29
+ "ops",
30
  "scaled_fp8_quant",
31
  "scaled_int8_quant",
32
  ]
build/torch25-cxx98-cu118-x86_64-linux/quantization/_quantization_0_0_1.abi3.so CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:25d0f8374e7023760dfedf2f99fb7d56c22f02f0f4b82634e6166515f111fcc2
3
- size 85709024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cb12611bb467ef6bdd2228303a8beebe83ca15230abd1ebd385bcca40201d11
3
+ size 87453464
build/torch25-cxx98-cu121-x86_64-linux/quantization/__init__.py CHANGED
@@ -13,6 +13,7 @@ from .marlin import (
13
  marlin_qqq_gemm,
14
  marlin_gemm,
15
  )
 
16
 
17
  __all__ = [
18
  "awq_marlin_repack",
@@ -25,6 +26,7 @@ __all__ = [
25
  "gptq_marlin_repack",
26
  "marlin_gemm",
27
  "marlin_qqq_gemm",
 
28
  "scaled_fp8_quant",
29
  "scaled_int8_quant",
30
  ]
 
13
  marlin_qqq_gemm,
14
  marlin_gemm,
15
  )
16
+ from ._ops import ops
17
 
18
  __all__ = [
19
  "awq_marlin_repack",
 
26
  "gptq_marlin_repack",
27
  "marlin_gemm",
28
  "marlin_qqq_gemm",
29
+ "ops",
30
  "scaled_fp8_quant",
31
  "scaled_int8_quant",
32
  ]
build/torch25-cxx98-cu121-x86_64-linux/quantization/_quantization_0_0_1.abi3.so CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e153ae86e155d6fc792f08b4986e899467299abe50e3d39519de4b7e7198a5fa
3
- size 105258480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36df22427383e6c3907fdf83264b6d9a67579c258feba09d5e75c72e5db2ef0e
3
+ size 107007424
build/torch25-cxx98-cu124-x86_64-linux/quantization/__init__.py CHANGED
@@ -13,6 +13,7 @@ from .marlin import (
13
  marlin_qqq_gemm,
14
  marlin_gemm,
15
  )
 
16
 
17
  __all__ = [
18
  "awq_marlin_repack",
@@ -25,6 +26,7 @@ __all__ = [
25
  "gptq_marlin_repack",
26
  "marlin_gemm",
27
  "marlin_qqq_gemm",
 
28
  "scaled_fp8_quant",
29
  "scaled_int8_quant",
30
  ]
 
13
  marlin_qqq_gemm,
14
  marlin_gemm,
15
  )
16
+ from ._ops import ops
17
 
18
  __all__ = [
19
  "awq_marlin_repack",
 
26
  "gptq_marlin_repack",
27
  "marlin_gemm",
28
  "marlin_qqq_gemm",
29
+ "ops",
30
  "scaled_fp8_quant",
31
  "scaled_int8_quant",
32
  ]
build/torch25-cxx98-cu124-x86_64-linux/quantization/_quantization_0_0_1.abi3.so CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e8016e26ae454e2c820104d11b44bd30adaffc112b70043daeb58bfb2fab9f1c
3
- size 109243600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77cbeca8bdda01afe774db01c4a817f20289cd4321e290887ded097c110046d7
3
+ size 110853464