Chendi.Xue 0a71900bc9 Remove hard-dependencies of Speculative decode to CUDA workers (#10587) ...

Signed-off-by: Chendi Xue <chendi.xue@intel.com>

2024-11-26 17:57:11 -08:00

..

__init__.py

[Hardware][NVIDIA] Add non-NVML CUDA mode for Jetson (#9735)

2024-11-26 10:26:28 -08:00

cpu.py

Remove hard-dependencies of Speculative decode to CUDA workers (#10587)

2024-11-26 17:57:11 -08:00

cuda.py

Remove hard-dependencies of Speculative decode to CUDA workers (#10587)

2024-11-26 17:57:11 -08:00

hpu.py

[torch.compile] support all attention backends (#10558)

2024-11-22 14:04:42 -08:00

interface.py

[torch.compile] support all attention backends (#10558)

2024-11-22 14:04:42 -08:00

neuron.py

[platforms] absorb worker cls difference into platforms folder (#10555)

2024-11-21 21:00:32 -08:00

openvino.py

[Bugfix] Avoid import AttentionMetadata explicitly in Mllama (#10593)

2024-11-23 18:12:20 +00:00

rocm.py

[torch.compile] support all attention backends (#10558)

2024-11-22 14:04:42 -08:00

tpu.py

[torch.compile] support all attention backends (#10558)

2024-11-22 14:04:42 -08:00

xpu.py

[torch.compile] support all attention backends (#10558)

2024-11-22 14:04:42 -08:00