youkaichao 76ed5340f0 [torch.compile] add deepseek v2 compile (#9775) ...

Signed-off-by: youkaichao <youkaichao@gmail.com>

2024-10-28 14:35:17 -07:00

..

guided_decoding

[Frontend] Bad words sampling parameter (#9717)

2024-10-26 16:29:38 +00:00

layers

[torch.compile] support moe models (#9632)

2024-10-27 21:58:04 -07:00

model_loader

[Hardware][openvino] is_openvino --> current_platform.is_openvino (#9716)

2024-10-26 10:59:06 +00:00

models

[torch.compile] add deepseek v2 compile (#9775)

2024-10-28 14:35:17 -07:00

__init__.py

[Performance] Optimize e2e overheads: Reduce python allocations (#7162)

2024-08-08 21:34:28 -07:00

custom_op.py

[Hardware][ROCM] using current_platform.is_rocm (#9642)

2024-10-28 04:07:00 +00:00

parameter.py

[Kernel] (2/N) Machete - Integrate into CompressedTensorsWNA16 and GPTQMarlin (#7701)

2024-09-23 13:46:26 -04:00

pooling_metadata.py

[Model][Misc] Add e5-mistral-7b-instruct and Embedding API (#3734)

2024-05-11 11:30:37 -07:00

sampling_metadata.py

[Spec Decode] (1/2) Remove batch expansion (#8839)

2024-10-01 16:04:42 -07:00

utils.py

[TPU] Call torch._sync(param) during weight loading (#9437)

2024-10-17 09:00:11 -07:00