youkaichao ff5ed6e1bc [torch.compile] rework compile control with piecewise cudagraph (#9715) ...

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

2024-10-29 23:03:49 -07:00

..

guided_decoding

[Frontend] Bad words sampling parameter (#9717)

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

layers

[Bugfix][VLM] Make apply_fp8_linear work with >2D input (#9812)

2024-10-29 19:49:44 -07:00

model_loader

[Bugfix] Fix prefix strings for quantized VLMs (#9772)

2024-10-29 16:02:59 -07:00

models

[Bugfix] Fix prefix strings for quantized VLMs (#9772)

2024-10-29 16:02:59 -07:00

__init__.py

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

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

custom_op.py

[torch.compile] rework compile control with piecewise cudagraph (#9715)

2024-10-29 23:03:49 -07:00

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

[Hardware] using current_platform.seed_everything (#9785)

2024-10-29 14:47:44 +00:00