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

@tduncan / Nvidia-Optimization-Stack-VLLM

Code Commits Issues Pulls Cloud Agent CI/CD

main

test_attention_backends.py

test_attention_backends_selection.py

test_attention_splitting.py

test_b12x.py

test_backend_per_kind.py

test_batch_reordering.py

test_chunked_local_attention.py

test_cpu_mla_backend.py

test_cuda_backend_probe_errors.py

test_dcp_a2a_pack_mask.py

test_deepseek_v4_rocm_adaptive.py

test_deepseek_v4_swa_visible.py

test_dspark_noncausal_sparse_mla.py

test_expand_page_indices.py

test_flashinfer_dcp_spec_reorder.py

test_flashinfer_mla_dcp.py

test_flashinfer_mla_sparse_sm90.py

test_flashinfer_sparse_mla_sm120_api.py

test_flashinfer_sparse_mla_workspace.py

test_flashmla_nope_sm90_backend_selection.py

test_gdn_metadata_builder.py

test_group_head_counts.py

test_group_sliding_window.py

test_indexer_dcp_localize.py

test_indexer_deepseek_v4_slot_mapping.py

test_indexer_native_next_n.py

test_kpool_tail_slot_mapping.py

test_kv_head_stride_canonicalization.py

test_linear_attention_metadata_builder.py

test_mamba_metadata_builder.py

test_mla_backends.py

test_mla_context_chunks.py

test_mla_noncausal.py

test_mla_prefill_quant_output.py

test_mla_prefill_registry.py

test_mla_prefill_selector.py

test_mm_prefix.py

test_replayssm_metadata_builder.py

test_rocm_aiter_mla_dcp_cprr.py

test_rocm_aiter_mla_dcp_cprr_numerics.py

test_rocm_aiter_mla_fp8_decode_routing.py

test_rocm_aiter_mla_mtp_split.py

test_rocm_aiter_triton_sparse_mla.py

test_rocm_attention_backends_selection.py

test_rocm_glm5next_sparse.py

test_rocm_paged_mxfp4_indexer_plan.py

test_sparse_indexer_decode_seq_lens.py

test_sparse_mla_backends.py

test_sparse_mla_kv_cache_layout.py

test_sparse_mla_mask.py

test_triton_attn_segments.py

test_trtllm_attention_integration.py

test_vit_attn_wrappers.py

utils.py