Lucas Wilkinson 8d7da92fd7 [BugFix] Fix default kv-cache-dtype default for DeepseekV3.2 (#25988) ...

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

2025-09-30 21:58:31 -07:00

..

layers

[Log] Optimize Log for FP8MOE (#25709)

2025-09-30 19:18:43 -07:00

model_loader

[CI/Build] Consolidate model loader tests and requirements (#25765)

2025-09-26 21:45:20 -07:00

models

[BugFix] Fix default kv-cache-dtype default for DeepseekV3.2 (#25988)

2025-09-30 21:58:31 -07:00

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