File size: 1,129 Bytes
132e594
6df83c0
132e594
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
[general]
name = "paged_attention"

[torch]
src = [
  "torch-ext/torch_binding.cpp",
  "torch-ext/torch_binding.h"
]

[kernel.cuda_utils]
src = [
  "cuda-utils/cuda_utils_kernels.cu",
]
depends = []
 

[kernel.paged_attention]
src = [
  "paged-attention/attention/attention_dtypes.h",
  "paged-attention/attention/attention_generic.cuh",
  "paged-attention/attention/attention_kernels.cuh",
  "paged-attention/attention/attention_utils.cuh",
  "paged-attention/attention/dtype_bfloat16.cuh",
  "paged-attention/attention/dtype_float16.cuh",
  "paged-attention/attention/dtype_float32.cuh",
  "paged-attention/attention/dtype_fp8.cuh",
  "paged-attention/attention/paged_attention_v1.cu",
  "paged-attention/attention/paged_attention_v2.cu",
  "paged-attention/cache_kernels.cu",
  "paged-attention/cuda_compat.h",
  "paged-attention/dispatch_utils.h",
  "paged-attention/quantization/fp8/amd/hip_float8.h",
  "paged-attention/quantization/fp8/amd/hip_float8_impl.h",
  "paged-attention/quantization/fp8/amd/quant_utils.cuh",
  "paged-attention/quantization/fp8/nvidia/quant_utils.cuh",
]
include = [ "." ]
depends = [ "torch" ]