Yuhao Yang 1240ac13b8 vlm: fix tiny multimodal cache bug (#12984)

2025-11-10 21:30:19 +08:00

..

compare.py

…

test_clip_models.py

…

test_compressed_tensors_models.py

…

test_cross_encoder_models.py

…

test_dummy_grok_models.py

…

test_embedding_models.py

Add support for Matryoshka embeddings (#126) (#11142)

2025-10-28 02:49:36 +08:00

test_encoder_embedding_models.py

…

test_falcon_h1_models.py

…

test_generation_models.py

[Model] Add Olmo 3 model support (#11396)

2025-10-19 23:59:16 -07:00

test_glm4_moe_models.py

[CI] Add GLM4MoE model test (#11706)

2025-10-16 16:25:58 +08:00

test_gme_qwen_models.py

…

test_grok_models.py

…

test_kimi_k2_models.py

Add kimi k2 thinking to ci (#12907)

2025-11-09 16:10:32 +08:00

test_kimi_linear_models.py

Support Kimi Linear (#12469)

2025-10-31 14:03:35 -07:00

test_llama4_models.py

…

test_mtp_models.py

…

test_nvidia_nemotron_nano_v2.py

Feature/nano v2 offline modelopt fp8 and nvfp4 (#12018)

2025-10-23 11:16:46 -07:00

test_qwen3_next_models.py

[Feature] Qwen3-Next & FLA: Support MTP topk>1; Up to 6% faster (#11133)

2025-11-01 19:47:56 -07:00

test_qwen_models.py

…

test_reward_models.py

…

test_transformers_models.py

Clean up server args (#8161)

2025-07-19 11:32:52 -07:00

test_unsloth_models.py

…

test_vlm_models.py

vlm: fix tiny multimodal cache bug (#12984)

2025-11-10 21:30:19 +08:00