Harry Mellor 458e74eb90 Support more parallel styles in Transformers backend TP (#22651) ...

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

2025-08-11 10:42:48 -07:00

..

layers

[Model] Pooling models default to using chunked prefill & prefix caching if supported. (#20930)

2025-08-11 09:41:37 -07:00

model_loader

Add ModelOpt Qwen3 nvfp4 support (#20101)

2025-08-07 19:18:19 -07:00

models

Support more parallel styles in Transformers backend TP (#22651)

2025-08-11 10:42:48 -07:00

warmup

[Docs] Fix warnings in docs build (#22588)

2025-08-10 05:49:51 -07:00

__init__.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

custom_op.py

Optimize configuration access with LRU cache in custom ops (#22204)

2025-08-04 21:43:24 -07:00

parameter.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

pooling_metadata.py

[Model][1/N] Support multiple poolers at model level (#21227)

2025-07-21 02:22:21 -07:00

sampling_metadata.py

Revert "Update sampling_metadata.py (#21937)" (#22088)

2025-08-01 05:24:46 -07:00

utils.py

[Quantization] Enable BNB support for InternS1 (#21953)

2025-08-01 11:09:54 +00:00