Max Hu 9c3fe9936b Flashinfer cuDNN backend for Qwen3 VL ViT attention (#34580) ...

Signed-off-by: Max Hu <maxhu@nvidia.com>
Signed-off-by: Max Hu <hyoung2991@gmail.com>
Co-authored-by: Max Hu <maxhu@nvidia.com>
Co-authored-by: Shang Wang <shangw@nvidia.com>

2026-02-27 20:20:23 +08:00

..

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

[Attn,KV-cache] Use per-head scales in the attention selector (#34281)

2026-02-24 09:02:43 -05:00

test_attention.py

[5/N][Attention] Finish eliminating vllm/attention folder (#32064)

2026-01-27 10:02:51 -05:00

test_cache.py

[Hardware][AMD][CI][Bugfix] Fix Kernels Attention Cache test (#32904)

2026-01-23 16:24:26 +00:00

test_cascade_flash_attn.py

[Platform] Deprecate seed_everything (#31659)

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

test_cpu_attn.py

[CPU] Split attention dispatch by head_dim alignment (#32161)

2026-02-03 19:37:15 -08:00

test_cutlass_mla_decode.py

[Platform] Add current_platform.num_compute_units interface (#35042)

2026-02-24 22:22:49 -08:00

test_deepgemm_attention.py

[Perf] Disable clean_logits in deepgemm fp8_mqa_logits kernel (#33568)

2026-02-05 20:34:00 -05:00

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

Revert "[Kernels][FI] Skip trtllm attention when num_kv_heads=1 (#308… (#31617)

2026-01-10 12:39:59 -08:00

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

Update FlashMLA (#32491)

2026-01-21 13:03:37 +08:00

test_flashmla.py

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

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

test_lightning_attn.py

[Platform] Deprecate seed_everything (#31659)

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

test_merge_attn_states.py

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

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

test_mha_attn.py

Flashinfer cuDNN backend for Qwen3 VL ViT attention (#34580)

2026-02-27 20:20:23 +08:00

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

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

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

test_rocm_attention_selector.py

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

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

test_triton_decode_attention.py

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

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

test_triton_prefill_attention.py

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

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

test_triton_unified_attention.py

Add unit tests for fp8 output fusion of triton_attn (#34228)

2026-02-18 06:22:49 -05:00