Isotr0py 3e274a0024 Merge remote-tracking branch 'origin/main' into qwen-image-2.1 ...

# Conflicts:
#	tests/entrypoints/openai_api/test_image_server.py
#	vllm_omni/entrypoints/openai/api_server.py

2026-09-22 01:23:45 +00:00

..

test_attention_config.py

[Bugfix] Isolate weekly CPU tests from inherited attention env and hf_api mocks (#7565)

2026-09-21 15:55:00 +00:00

test_attention_sp.py

[Bugfix] Support GQA/MQA in the ring attention SDPA path (#5255)

2026-08-07 04:08:33 +00:00

test_block_sparse_ops.py

[Attention] [P1] Keep H3 VSA policy in the model and share sparse primitives (#7535)

2026-09-16 15:47:31 +08:00

test_cuda_backend_selection.py

[CI] Select mirror_hardwares presets via MIRROR_HW (H100/B200) (#5543)

2026-09-02 15:39:49 +00:00

test_cudnn_attn.py

Optimize Qwen-Image 2.1 attention and decode graph reuse (#7790)

2026-09-18 19:37:19 +08:00

test_fastvideo_vsa.py

[Attention] [P1] Keep H3 VSA policy in the model and share sparse primitives (#7535)

2026-09-16 15:47:31 +08:00

test_flash_attn_npu.py

[Bugfix][NPU] Materialize causal mask in FlashAttention dense path (#7324)

2026-09-14 01:46:29 +00:00

test_flash_attn.py

[CI/Build][ROCm] Stabilize shared AMD test lanes (#7706)

2026-09-18 11:13:07 +08:00

test_flashinfer_attn.py

[CI] Select mirror_hardwares presets via MIRROR_HW (H100/B200) (#5543)

2026-09-02 15:39:49 +00:00

test_impl_overrides.py

[Attention] [P1] Keep H3 VSA policy in the model and share sparse primitives (#7535)

2026-09-16 15:47:31 +08:00

test_kernels_hub.py

[Bugfix] Resolve #6931 hub FA3 on torch 2.13 via kernels 0.16.1 (#7185)

2026-09-09 10:20:34 +00:00

test_mindie_public_integration.py

[Hardware][Ascend] Integrate MindIE dense and sparse quantized attention for Wan2.2 T2V (#7561)

2026-09-18 01:28:27 +00:00

test_mindie_runtime.py

[Bugfix][RAINFUSION_ATTN] Fix padding-mask rejection on packed [real, pad] layouts and reuse query tail as output padding (#7235)

2026-09-20 10:56:51 +08:00

test_piecewise_attn.py

[Diffusion] Add paged KV cache support for HunyuanImage3 DiT on NPU and GPU (#6563)

2026-08-31 10:15:46 +00:00

test_rainfusion_plan.py

[Bugfix][RAINFUSION_ATTN] Fix padding-mask rejection on packed [real, pad] layouts and reuse query tail as output padding (#7235)

2026-09-20 10:56:51 +08:00

test_ring_backend_selection.py

[CI] Select mirror_hardwares presets via MIRROR_HW (H100/B200) (#5543)

2026-09-02 15:39:49 +00:00

test_ring_fa4.py

[CI] Select mirror_hardwares presets via MIRROR_HW (H100/B200) (#5543)

2026-09-02 15:39:49 +00:00

test_ring_padding.py

[Model][MiniMax-H3] Multi-GPU serving fixes and layer-wise offload component selection (#7047)

2026-09-14 10:02:30 -07:00

test_ring_utils.py

[CI] Select mirror_hardwares presets via MIRROR_HW (H100/B200) (#5543)

2026-09-02 15:39:49 +00:00

test_sage_attn3.py

[CI] Select mirror_hardwares presets via MIRROR_HW (H100/B200) (#5543)

2026-09-02 15:39:49 +00:00

test_sage_attn.py

[CI] Select mirror_hardwares presets via MIRROR_HW (H100/B200) (#5543)

2026-09-02 15:39:49 +00:00

test_sdpa.py

[Feature] Add AllGather-KV sequence-parallel attention str… (#4968)

2026-07-24 14:45:26 +00:00

test_selector.py

[CI] Select mirror_hardwares presets via MIRROR_HW (H100/B200) (#5543)

2026-09-02 15:39:49 +00:00

test_trtllm_attn.py

[perf] Add mask-free TRTLLM packed-padding path (#6542)

2026-08-25 07:45:21 +00:00

test_trtllm_calibration.py

[Attention] Add trtllm diffusion attention backend with Skip-Softmax (#5283)

2026-07-27 22:48:11 +08:00

test_ulysses_uaa.py

[Perf][Diffusion] Skip the Ulysses length all-gather when shards are padded equal (#5717)

2026-09-06 16:23:30 +08:00