Isotr0py 55f1fc1b1b [v1] Add PrefixLM support to TritonAttention backend (#30386) ...

(cherry picked from commit 74a1ac38b00a8cf502db085d1bbd77712cf47e41)

2025-12-17 19:57:52 -08:00

..

vlm_utils

[ROCm][CI][Bugfix] Fixing the Multi-Modal Models Test (Extended) 1 group (#30013)

2025-12-04 11:00:16 +00:00

__init__.py

…

conftest.py

[ROCm][CI][Bugfix] Fixing the Multi-Modal Models Test (Extended) 1 group (#30013)

2025-12-04 11:00:16 +00:00

test_audioflamingo3.py

Add AudioFlamingo3 model support (#30539)

2025-12-14 02:14:55 -08:00

test_common.py

[v1] Add PrefixLM support to FlexAttention backend (#27938)

2025-12-07 15:51:36 +00:00

test_granite_speech.py

[ROCm][CI][Bugfix] Fixing the Multi-Modal Models Test (Extended) 1 group (#30013)

2025-12-04 11:00:16 +00:00

test_interleaved.py

…

test_keye.py

[Bugfix] [Model] Missing MRoPE function definition from KeyeForConditionalGeneration (#27895)

2025-11-01 13:45:23 +08:00

test_maverick.py

…

test_multimodal_gguf.py

[v1] Add PrefixLM support to TritonAttention backend (#30386)

2025-12-17 19:57:52 -08:00

test_phi4mm.py

VLLM_USE_TRITON_FLASH_ATTN V0 variable deprecation (#27611)

2025-11-11 18:34:36 -08:00

test_pixtral.py

[ROCm][CI][Bugfix] Fixing the Multi-Modal Models Test (Extended) 1 group (#30013)

2025-12-04 11:00:16 +00:00

test_qwen2_5_vl.py

Avoid bytecode hook and simplify TorchCompileWrapperWithCustomDipatch (#25110)

2025-11-14 14:11:10 -08:00

test_qwen2_vl.py

[Model][QwenVL] Replace torch.repeat_interleave with faster np.repeat (#28964)

2025-11-19 22:04:23 -08:00

test_ultravox.py

…

test_vit_backend_functionality.py

[CI/Build] Skip broken ViT backend functionality test tempoarily (#30782)

2025-12-16 17:15:26 -08:00

test_voxtral.py

[Chore] Adjust tokenizer import to avoid circular imports (#30601)

2025-12-13 04:42:39 -08:00

test_whisper.py

[CI] Whisper logprobs tests (#30504)

2025-12-13 10:49:11 +08:00