tests/kernels/attention · tduncan/Nvidia-Optimization-Stack-VLLM · siGit Code & Deploy

@tduncan / Nvidia-Optimization-Stack-VLLM

Code Commits Issues Pulls Cloud Agent CI/CD

main

conftest.py

test_amx_mla.py

test_attention.py

test_attention_selector.py

test_cache.py

test_cascade_flash_attn.py

test_cpu_attn.py

test_cutlass_mla_decode.py

test_deepgemm_attention.py

test_flash_attn.py

test_flashinfer.py

test_flashinfer_mla_decode.py

test_flashinfer_trtllm_attention.py

test_flashmla.py

test_flashmla_sparse.py

test_kimi_k3_mla_fused_epilogue.py

test_kimi_k3_mla_key_concat_kv_cache.py

test_lightning_attn.py

test_merge_attn_states.py

test_mha_attn.py

test_minimax_m3.py

test_minimax_m3_fp8_triton_indexer.py

test_minimax_m3_msa_cutlass_sparse_decode.py

test_mixed_causal_attn.py

test_mla_cross_layer_kernel_equivalence.py

test_mla_decode_cpu.py

test_pack_unpack_triton.py

test_prefix_prefill.py

test_rocm_aiter_candidate_mask.py

test_rocm_aiter_fa.py

test_rocm_aiter_mla_causal_verify_mask.py

test_rocm_aiter_mla_decode.py

test_rocm_aiter_mla_decode_metadata.py

test_rocm_aiter_mla_fp8_prefill.py

test_rocm_aiter_mla_fp8_support.py

test_rocm_aiter_mla_head_padding.py

test_rocm_aiter_mla_op_registration.py

test_rocm_aiter_mla_sink.py

test_rocm_aiter_mla_sparse_metadata_sync.py

test_rocm_aiter_unified_attn.py

test_rocm_paged_mxfp4_indexer.py

test_rocm_triton_attn_dsv4.py

test_triton_decode_attention.py

test_triton_mla_causal_verify_flatten.py

test_triton_prefill_attention.py

test_triton_unified_attention.py

test_triton_unified_attention_diffkv.py

test_trtllm_kvfp8_dequant.py

test_use_trtllm_attention.py

test_xpu_mla_sparse.py