Eugene KhvedchenyaandRoger Wang 392edee34a EVS Support (Video tokens pruning) (#22980) ...

Signed-off-by: Eugene Khvedchenia <ekhvedchenia@nvidia.com>
Signed-off-by: Eugene Khvedchenya <ekhvedchenya@gmail.com>
Co-authored-by: Roger Wang <hey@rogerw.io>

2025-09-26 11:54:54 +08:00

..

layers

Llamas 3.1 405B fp4 changes upstreaming from 355_wip (#25135)

2025-09-25 19:16:53 -06:00

model_loader

[Optimization] Use a cheaper cache key in get_model_architecture (#25682)

2025-09-25 17:54:20 -04:00

models

EVS Support (Video tokens pruning) (#22980)

2025-09-26 11:54:54 +08:00

warmup

[V0 deprecation] Remove _VLLM_V1 suffixes from attention backend names (#25489)

2025-09-25 17:37:50 +00:00

__init__.py

[V0 Deprecation] Remove V0 sampling metadata (#25345)

2025-09-21 10:37:11 -07:00

custom_op.py

[V0 deprecation] Deprecate V0 Neuron backend (#21159)

2025-09-06 16:15:18 -07:00

parameter.py

Revert "[Bug] Dynamo Unsupported due to BasevLLMParameter.torch_function calling disabled super()" (#25681)

2025-09-25 09:45:06 -07:00

utils.py

[OOT] Support sync_model_loading for OOT (#25126)

2025-09-19 05:41:53 +00:00