Zhanda Zhu 5d5c776444 [Perf] FP8 FlashInfer Attn for ViT (#38065) ...

Signed-off-by: Zhanda Zhu <zhandazhu@gmail.com>
Co-authored-by: Yubo Gao <ybgao-nvidia@users.noreply.github.com>

2026-04-27 13:44:15 +08:00

..

base_model_arch_groundtruth.json

[Bugfix] add support for 'num_attention_groups' in ModelArchConfigConvertorBase for Step3p5 (#39796)

2026-04-16 05:48:00 +00:00

draft_model_arch_groundtruth.json

[BugFix]Fix eagle draft_model_config and add tests (#31753)

2026-01-12 23:09:36 -08:00

test_config_generation.py

[ROCm] [CI] fix test_unrecognized_env (#34350)

2026-02-11 18:50:44 +00:00

test_config_utils.py

[fix] add VLLM_OBJECT_STORAGE_SHM_BUFFER_NAME to compile factors (#32912)

2026-01-23 22:53:10 +00:00

test_config_with_model.yaml

[V0 Deprecation] Remove multi-step scheduling (#22138)

2025-08-12 20:18:39 -07:00

test_config.yaml

[V0 Deprecation] Remove multi-step scheduling (#22138)

2025-08-12 20:18:39 -07:00

test_model_arch_config.py

[Bugfix] add support for 'num_attention_groups' in ModelArchConfigConvertorBase for Step3p5 (#39796)

2026-04-16 05:48:00 +00:00

test_mp_reducer.py

[V0 Deprecation] Remove VLLM_USE_V1 from tests (#26341)

2025-10-07 15:42:31 +00:00

test_multimodal_config.py

[Perf] FP8 FlashInfer Attn for ViT (#38065)

2026-04-27 13:44:15 +08:00