leideng/QCFuse / srt /layers /attention
466 GB
2,808 files
Updated 24 days ago
Name
Size
fla
mamba
npu_ops
nsa
triton_ops
wave_ops
aiter_backend.py43.9 kB
xet
ascend_backend.py27.9 kB
xet
attention_registry.py7.51 kB
xet
base_attn_backend.py5.24 kB
xet
cutlass_mla_backend.py9.85 kB
xet
double_sparsity_backend.py9.14 kB
xet
dual_chunk_flashattention_backend.py68.6 kB
xet
flashattention_backend.py106 kB
xet
flashinfer_backend.py65.9 kB
xet
flashinfer_mla_backend.py39.5 kB
xet
flashmla_backend.py20.9 kB
xet
hybrid_attn_backend.py5.12 kB
xet
hybrid_linear_attn_backend.py26.1 kB
xet
intel_amx_backend.py4.17 kB
xet
merge_state.py1.42 kB
xet
nsa_backend.py45.5 kB
xet
tbo_backend.py9.19 kB
xet
torch_flex_backend.py11.7 kB
xet
torch_native_backend.py9.73 kB
xet
triton_backend.py59.3 kB
xet
trtllm_mha_backend.py27.5 kB
xet
trtllm_mla_backend.py41.7 kB
xet
utils.py3.23 kB
xet
vision.py21.8 kB
xet
vision_utils.py2.77 kB
xet
wave_backend.py22.9 kB
xet
xpu_backend.py47.7 kB
xet
Total size
466 GB
Files
2,808
Last updated
Jun 16
Pre-warmed CDN
US EU US EU

Contributors