vLLM/tests/kernels/attention at e8d3e22c884e95a7499ffcf37fa932751f0780df - vLLM

conftest.py

[Chore] Clean up pytorch helper functions in vllm.utils (#26908 )

2025-10-18 09:48:22 -07:00

test_aiter_flash_attn.py

[ROCm][AITER] Fix AITER import regression for explicit backend selection (#33749 )

2026-02-06 15:08:16 +00:00

test_attention_selector.py

[FlashAttn] Fix supports_kv_cache_dtype() accepting unhandled fp8 kv-cache dtype variants (#42685 )

2026-05-15 15:34:59 -04:00

test_attention.py

[Hardware] Replace torch.cuda.device_count/current_device/set_device API (#36145 )

2026-03-12 07:57:47 -07:00

test_cache.py

Add nvfp4 support to reshape_and_cache_flash (#37332 )

2026-04-17 07:28:00 -07:00

test_cascade_flash_attn.py

[Platform] Deprecate seed_everything (#31659 )

2026-01-04 18:34:04 -08:00

test_cpu_attn.py

[CPU] Refine CPU attention frontend (#45391 )

2026-06-14 19:26:54 -07:00

test_cutlass_mla_decode.py

[Hardware] Replace torch.cuda.device_count/current_device/set_device API (#36145 )

2026-03-12 07:57:47 -07:00

test_deepgemm_attention.py

[Feat] DeepSeek V4 Rebased (#40860 )

2026-04-26 18:31:08 -07:00

test_flash_attn.py

[Platform] Deprecate seed_everything (#31659 )

2026-01-04 18:34:04 -08:00

test_flashinfer_mla_decode.py

[CI/Build][AMD] Fix import errors in tests/kernels/attention (#29032 )

2025-11-20 17:48:09 +08:00

test_flashinfer_trtllm_attention.py

Add nvfp4 kv cache support (#40177 )

2026-05-01 04:55:16 +00:00

test_flashinfer.py

[Update] Use FlashInfer fast_decode_plan directly instead of replication (#34687 )

2026-02-26 16:31:43 -08:00

test_flashmla_sparse.py

[Bug] Fix test flashmla for DSv4 (#45052 )

2026-06-11 16:22:26 -04:00

test_flashmla.py

[Hardware] Replace torch.cuda.device_count/current_device/set_device API (#36145 )

2026-03-12 07:57:47 -07:00

test_lightning_attn.py

[Kernel][Test] Extend lightning_attn and awq_triton kernel tests to XPU (#43307 )

2026-06-04 14:25:59 -04:00

test_merge_attn_states.py

[Kernel] Fuse FP8 output quantization into merge_attn_states (#36518 )

2026-04-03 01:47:04 +00:00

test_mha_attn.py

[MM][OOT] Support CPU seq_lens for OOT MMEncoderAttention kernels (#36605 )

2026-03-12 03:28:23 -07:00

test_mixed_causal_attn.py

[Model] Add DiffusionGemma Support (#45163 )

2026-06-11 22:17:35 -07:00

test_mla_decode_cpu.py

[Chore]:Extract math and argparse utilities to separate modules (#27188 )

2025-10-26 04:03:32 -07:00

test_pack_unpack_triton.py

[1/N][Attention] Restructure attention: move files (#31916 )

2026-01-09 13:10:24 -08:00

test_prefix_prefill.py

[Hardware] Replace torch.cuda.device_count/current_device/set_device API (#36145 )

2026-03-12 07:57:47 -07:00

test_rocm_aiter_unified_attn.py

[ROCm][CI] Add test for Aiter unified attn kernel (#44436 )

2026-06-04 16:15:05 +00:00

test_rocm_attention_selector.py

[1/N][Attention] Restructure attention: move files (#31916 )

2026-01-09 13:10:24 -08:00

test_rocm_triton_attn_dsv4.py

[ROCm][DSV4][Perf] Fuse inverse-RoPE and cache bf16 wo_a in o-projection (#45103 )

2026-06-12 15:57:09 -05:00

test_triton_decode_attention.py

[XPU] enable triton attention test on XPU by removing cuda device binding (#39627 )

2026-04-20 20:57:11 +08:00

test_triton_prefill_attention.py

[XPU] enable triton attention test on XPU by removing cuda device binding (#39627 )

2026-04-20 20:57:11 +08:00

test_triton_unified_attention_diffkv.py

[Attention] add triton diff-kv backend for mimo (#41797 )

2026-06-11 11:36:31 -04:00

test_triton_unified_attention.py

[feat] Add FP8 per-tensor Q scale support to Triton attention backend (#42080 )

2026-05-19 09:02:05 -07:00

test_trtllm_kvfp8_dequant.py

[ROCm][CI] Skip trtllm kvfp8 dequant tests on ROCm (#37330 )

2026-03-18 11:12:26 +08:00

test_use_trtllm_attention.py

[CI/Build] Skip test_use_trtllm_attention on non-CUDA platforms (#44687 )

2026-06-10 18:18:42 -04:00

test_xpu_mla_sparse.py

Add XPU MLA Sparse backend for DeepSeek v3.2 (#33230 )

2026-03-11 19:19:15 +08:00