Lucas Wilkinson 2e6bc46821 [Startup] Make DeepGEMM warmup scale with max-num-batched-tokens (#24693) ...

Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>

2025-09-11 20:10:19 -04:00

..

layers

[Bug] Fix Layer weight_block_size Assertion Issue (#24674)

2025-09-11 19:47:59 -04:00

model_loader

Fix typing for safetensors_load_strategy (#24641)

2025-09-11 10:41:39 +00:00

models

[Ultravox] Use wrapped_model_config to instantiate inner model (#24679)

2025-09-11 18:52:24 +00:00

warmup

[Startup] Make DeepGEMM warmup scale with max-num-batched-tokens (#24693)

2025-09-11 20:10:19 -04:00

__init__.py

[Misc] Add SPDX-FileCopyrightText (#19100)

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

custom_op.py

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

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

parameter.py

[Core] Allow disabling TP sharding for parallel Linear layer (#23024)

2025-09-05 22:53:58 -07:00

sampling_metadata.py

[Doc]: fix typos in Python comments (#24042)

2025-09-01 19:07:45 -07:00

utils.py

[Bugfix] Fix _synced_weight_loader (#24565)

2025-09-11 16:52:33 +08:00