Xiangyu Li 5cc6bddb6e [Kernel] Add GPTQv2 format support for low-bit or asymmetric quantization, by adapting gptq_gemm (#26092)

2025-10-23 23:26:13 -04:00

..

__init__.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

allspark.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

bitblas.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

conch.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

cutlass.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

dynamic_4bit.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

exllama.py

[Kernel] Add GPTQv2 format support for low-bit or asymmetric quantization, by adapting gptq_gemm (#26092)

2025-10-23 23:26:13 -04:00

machete.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

marlin.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

MPLinearKernel.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00