Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up

kernels-community
/
paged-attention

kernel
Model card Files Files and versions
xet
Community
2
paged-attention / paged-attention /attention
  • 5 contributors
History: 1 commit
danieldk's picture
danieldk HF Staff
Port vLLM attention kernels
132e594 8 months ago
  • attention_dtypes.h
    160 Bytes
    Port vLLM attention kernels 8 months ago
  • attention_generic.cuh
    1.73 kB
    Port vLLM attention kernels 8 months ago
  • attention_kernels.cuh
    28.6 kB
    Port vLLM attention kernels 8 months ago
  • attention_utils.cuh
    1.88 kB
    Port vLLM attention kernels 8 months ago
  • dtype_bfloat16.cuh
    12.3 kB
    Port vLLM attention kernels 8 months ago
  • dtype_float16.cuh
    12.1 kB
    Port vLLM attention kernels 8 months ago
  • dtype_float32.cuh
    5.64 kB
    Port vLLM attention kernels 8 months ago
  • dtype_fp8.cuh
    607 Bytes
    Port vLLM attention kernels 8 months ago
  • paged_attention_v1.cu
    8.79 kB
    Port vLLM attention kernels 8 months ago
  • paged_attention_v2.cu
    9.56 kB
    Port vLLM attention kernels 8 months ago