vllm/v1/attention/backends · tduncan/Nvidia-Optimization-Stack-VLLM · siGit Code & Deploy

@tduncan / Nvidia-Optimization-Stack-VLLM

Code Commits Issues Pulls Cloud Agent CI/CD

main

mla

__init__.py

b12x.py

composite.py

cpu_attn.py

fa_utils.py

flash_attn.py

flash_attn_diffkv.py

flashinfer.py

flex_attention.py

gdn_attn.py

hpc_attn.py

linear_attn.py

mamba1_attn.py

mamba2_attn.py

mamba_attn.py

recoverssm_metadata.py

registry.py

rocm_aiter_fa.py

rocm_aiter_unified_attn.py

rocm_attn.py

short_conv_attn.py

triton_attn.py

triton_attn_diffkv.py

triton_flash_attn.py

triton_flashinfer.py

turboquant_attn.py

utils.py

zentorch_sdpa.py