vLLM/tests/v1/attention at bfdbfa1632ef638db7d201f366c6f46cc26ca2b6 - vLLM

test_aiter_mla_uniform_mtp_qo_len.py

[ROCm][MLA] Cut ~21x host dispatch from the MLA metadata build (#58381 )

2026-10-12 13:11:20 -05:00

test_attention_backends_selection.py

[Bugfix] Fix Mamba page size AssertionError with spec decoding on GraniteMoeHybrid, FalconH1 and Zamba2 (#59975 )

2026-10-05 12:49:47 +00:00

test_attention_backends.py

[CI] Use an ungated model in the DGX Spark XQA test (#61416 )

2026-10-14 17:04:07 +00:00

test_attention_splitting.py

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212 )

2026-09-16 10:57:24 -07:00

test_b12x.py

[Kernel] Add B12X causal paged attention backend (#52017 )

2026-09-01 10:42:02 -04:00

test_backend_per_kind.py

[Kernel] Resubmit PR 48666 - Gemma4 FP8 KV FA4 head dim 512 backend selection (#53175 )

2026-09-23 20:29:06 -07:00

test_batch_reordering.py

[Attention] Support distinguishing between short extends and decodes (#37303 )

2026-03-20 10:49:36 -07:00

test_chunked_local_attention.py

[Deprecation] Deprecate items scheduled for 0.29 (#55353 )

2026-09-11 08:17:02 -07:00

test_cpu_mla_backend.py

[Attention][CPU] Use zentorch SDPA for CPU MLA prefill (#54967 )

2026-09-27 08:30:55 +00:00

test_cuda_backend_probe_errors.py

[Model] add GLM-5.3-Flash support (#53906 )

2026-09-03 09:40:35 -07:00

test_dcp_a2a_pack_mask.py

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212 )

2026-09-16 10:57:24 -07:00

test_deepseek_v4_rocm_adaptive.py

[ROCm][DSv4] Enable DSpark adaptive verification (#52362 )

2026-09-21 10:03:41 -05:00

test_deepseek_v4_swa_visible.py

[Spec Decode] Skip metadata build for dflash/dspark when all model backends support it (#60692 )

2026-10-12 00:09:10 -07:00

test_dspark_noncausal_sparse_mla.py

[KV Cache] GLM-5.3-Flash: use the generic packed KV layout; CircularBufferSpec tail with speculative ring slots (#57169 )

2026-10-09 15:48:37 -04:00

test_expand_page_indices.py

[ROCm][Perf] Parallelise AITER MLA page-index expansion over token chunks (#57978 )

2026-10-01 12:00:15 -05:00

test_flashinfer_dcp_spec_reorder.py

[Attention] Extend XQA decode support on SM90 (#50439 )

2026-09-11 06:19:55 +00:00

test_flashinfer_mla_dcp.py

[Spec decode] Support variable-length decode for Kimi-K3 adaptive ver (#52988 )

2026-09-22 20:43:32 -07:00

test_flashinfer_mla_sparse_sm90.py

[KV Cache] GLM-5.3-Flash: use the generic packed KV layout; CircularBufferSpec tail with speculative ring slots (#57169 )

2026-10-09 15:48:37 -04:00

test_flashinfer_sparse_mla_sm120_api.py

[Bugfix][SM120][MLA] Disable dense prefill for FlashInfer sparse MLA (#51395 )

2026-08-17 16:58:02 -07:00

test_flashinfer_sparse_mla_workspace.py

[Bugfix][Attention] Stabilize sparse-MLA DCP for GLM PCP evals (#55879 )

2026-09-15 09:58:30 -07:00

test_flashmla_nope_sm90_backend_selection.py

[Attention] Enable FA4 sparse MQA decode on Blackwell (#55866 )

2026-10-13 09:31:37 -04:00

test_gdn_aiter_flydsl.py

[ROCm][Perf] Make AITER FlyDSL GDN prefill default on gfx942/gfx950 (#60645 )

2026-10-14 10:11:57 +00:00

test_gdn_metadata_builder.py

[Perf][GDN] Internal prefill checkpoints for the FlashInfer GDN prefill backend (#60050 )

2026-10-14 14:49:46 +08:00

test_gdn_zero_draft_spec_rows.py

[Bugfix] Route every speculation-capable row through the speculative path so recurrent state stays consistent (#56531 )

2026-10-06 03:03:44 +04:00

test_glm5next_indexer_block_sizes.py

[KV Cache] GLM-5.3-Flash: use the generic packed KV layout; CircularBufferSpec tail with speculative ring slots (#57169 )

2026-10-09 15:48:37 -04:00

test_group_head_counts.py

[PCP][DCP] Support DCP target model with non-DCP Dspark (#56723 )

2026-09-26 18:12:35 -04:00

test_group_sliding_window.py

[Bugfix] Take the sliding window from the layer, not the KV cache group (#51756 )

2026-08-11 09:10:46 -07:00

test_indexer_dcp_localize.py

[Perf][Attention] Reduce GLM sparse MLA preparation overhead (#57458 )

2026-09-21 17:24:25 -07:00

test_indexer_deepseek_v4_slot_mapping.py

[Kernel][Build] Bump DeepGEMM to the 26/09/30 release and adapt the sparse indexer (#61149 )

2026-10-12 23:24:43 -07:00

test_indexer_native_next_n.py

[Attention][DSA] Take the native decode path for MTP=3 on SM90 (#52164 )

2026-08-14 10:09:51 +00:00

test_indexer_tp_row_shard.py

[Perf][GLM-5.3-Flash] Shard long-context indexer prefill rows across TP (#54951 )

2026-10-11 10:43:37 -04:00

test_kpool_indexer_block_sizes.py

[KV Cache] GLM-5.3-Flash: use the generic packed KV layout; CircularBufferSpec tail with speculative ring slots (#57169 )

2026-10-09 15:48:37 -04:00

test_kpool_tail_slot_mapping.py

[KV Cache] GLM-5.3-Flash: use the generic packed KV layout; CircularBufferSpec tail with speculative ring slots (#57169 )

2026-10-09 15:48:37 -04:00

test_kv_head_stride_canonicalization.py

[Attention] Make FlexAttention and FlashAttention use num-blocks first layouts (#42095 )

2026-05-26 19:55:56 -07:00

test_linear_attention_metadata_builder.py

[Feature] Support MTP speculative decoding for Bailing hybrid models (#44880 )

2026-07-06 10:38:50 +08:00

test_mamba2_prefill_checkpoints.py

[Bugfix][Prefix caching] Fix inconsistent hybrid Mamba prefix cache boundaries (#60533 )

2026-10-08 18:33:48 +00:00

test_mamba_metadata_builder.py

[Core] Remove deprecated mamba_cache_mode "all" (#58997 )

2026-10-01 02:59:37 -07:00

test_mla_backends.py

[Perf] Support minimum KV splits configuration for TokenSpeed MLA decode (#60345 )

2026-10-09 23:33:47 +00:00

test_mla_context_chunks.py

[3/N] HiSparse: host-resident sparse-MLA decode hot-buffering (#53781 )

2026-09-12 00:36:47 -04:00

test_mla_noncausal.py

[Bugfix][MLA] Scope DSpark non-causal capability to builder layers (#57992 )

2026-10-07 10:22:32 -05:00

test_mla_prefill_quant_output.py

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212 )

2026-09-16 10:57:24 -07:00

test_mla_prefill_registry.py

[Attention] Fetch MLA prefill workspace at use instead of init (#60654 )

2026-10-13 17:25:03 +00:00

test_mla_prefill_selector.py

[Platform] Support platform-specific MLA prefill backend selection (#56959 )

2026-10-08 15:25:21 +00:00

test_mm_prefix.py

[KV Cache] GLM-5.3-Flash: use the generic packed KV layout; CircularBufferSpec tail with speculative ring slots (#57169 )

2026-10-09 15:48:37 -04:00

test_replayssm_metadata_builder.py

[Mamba] Add FlashInfer ReplaySSM support for MTP (#52928 )

2026-09-30 21:41:17 +00:00

test_rocm_aiter_mla_dcp_cprr_numerics.py

[ROCm][MLA] Route gfx942 DCP causal multi-token verify to Triton split-KV decode (#58555 )

2026-10-14 10:17:15 +08:00

test_rocm_aiter_mla_dcp_cprr.py

[ROCm][MLA] Route gfx942 DCP causal multi-token verify to Triton split-KV decode (#58555 )

2026-10-14 10:17:15 +08:00

test_rocm_aiter_mla_dcp_verify_gfx942.py

[ROCm][MLA] Route gfx942 DCP causal multi-token verify to Triton split-KV decode (#58555 )

2026-10-14 10:17:15 +08:00

test_rocm_aiter_mla_fp8_decode_routing.py

[CI][ROCM] Add the Fusion E2E TP2 Quick group on MI355, and the AITER MLA fix it needs (#58369 )

2026-09-23 21:01:58 -05:00

test_rocm_aiter_mla_mtp_split.py

[ROCm][MLA] Route gfx942 DCP causal multi-token verify to Triton split-KV decode (#58555 )

2026-10-14 10:17:15 +08:00

test_rocm_aiter_mla_sparse.py

[ROCm][Perf] Skip cleaning sparse prefill MQA logits (#51314 )

2026-10-13 00:21:52 -05:00

test_rocm_aiter_triton_sparse_mla.py

[ROCm][Perf] Skip redundant sparse index remap on non-indexer layers (#51309 )

2026-10-13 05:25:56 +00:00

test_rocm_attention_backends_selection.py

[Bugfix][Compile] Replace Transformers AOT caching with graph caching (#58918 )

2026-10-13 19:17:29 +00:00

test_rocm_glm5next_sparse.py

[Perf] [Feat] [ROCm] Add densemha support to ROCm AITER Sparse MLA (#49263 )

2026-10-12 15:50:28 +00:00

test_rocm_mla_dcp_context.py

[ROCm][MLA] Keep DCP prefill context in FP8 through AllGather (#59070 )

2026-10-13 09:20:38 +08:00

test_rocm_paged_mqa_context_lens.py

[ROCm][Bugfix] Pass per-sequence context lengths to the AITER paged MQA-logits kernels (#59420 )

2026-10-09 08:16:20 +00:00

test_rocm_paged_mxfp4_indexer_plan.py

[Kernel][Build] Bump DeepGEMM to the 26/09/30 release and adapt the sparse indexer (#61149 )

2026-10-12 23:24:43 -07:00

test_sparse_indexer_decode_seq_lens.py

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212 )

2026-09-16 10:57:24 -07:00

test_sparse_mla_backends.py

[HiSparse] Read GPU-resident KV directly for mixed and BF16 prefills (#60417 )

2026-10-13 16:40:20 -04:00

test_sparse_mla_kv_cache_layout.py

[Attention] Enable FA4 sparse MQA decode on Blackwell (#55866 )

2026-10-13 09:31:37 -04:00

test_sparse_mla_mask.py

[Attention] Vectorize sparse MLA mask loads (#52217 )

2026-08-18 20:32:41 -07:00

test_triton_attn_metadata_builder.py

[Spec Decode] Skip metadata build for dflash/dspark when all model backends support it (#60692 )

2026-10-12 00:09:10 -07:00

test_triton_attn_segments.py

[Attention][Spec Decode] Multi-query Triton split-K for spec-decode verify, with empty-segment/padding hardening (#56148 )

2026-10-13 04:37:56 +04:00

test_trtllm_attention_integration.py

[Perf][Spec Decode] Enable fused multi-step draft decode for FlashInfer trtllm-gen (#58371 )

2026-09-29 06:06:47 +00:00

test_vit_attn_wrappers.py

[MM] Fix compiled ViT attention output layouts (#58182 )

2026-09-29 06:27:03 -07:00

utils.py

[Refactor] Remove dead tests utils (#58803 )

2026-09-26 09:16:53 -04:00