alexm-nm 7038e8b803 [Kernel] Support running GPTQ 8-bit models in Marlin (#4533)

2024-05-02 12:56:22 -04:00

..

attention

…

core

[mypy][6/N] Fix all the core subdirectory typing (#4450)

2024-05-02 03:01:00 +00:00

distributed

[Core][Distributed] enable multiple tp group (#4512)

2024-05-02 04:28:21 +00:00

engine

…

entrypoints

…

executor

…

logging

[MISC] Rework logger to enable pythonic custom logging configuration to be provided (#4273)

2024-05-01 17:34:40 -07:00

lora

…

model_executor

[Kernel] Support running GPTQ 8-bit models in Marlin (#4533)

2024-05-02 12:56:22 -04:00

spec_decode

…

transformers_utils

…

usage

…

worker

…

__init__.py

…

_custom_ops.py

[Kernel] Support running GPTQ 8-bit models in Marlin (#4533)

2024-05-02 12:56:22 -04:00

block.py

…

config.py

…

logger.py

[MISC] Rework logger to enable pythonic custom logging configuration to be provided (#4273)

2024-05-01 17:34:40 -07:00

outputs.py

…

py.typed

…

sampling_params.py

…

sequence.py

…

test_utils.py

…

utils.py

…