Merge 37f0b41ac6501266a661ebda3b1eff7bea9f3a1b into 9b4e9788e4a3a731f7567338ed15d3ec549ce03b

This commit is contained in:
Arupm 2025-08-29 20:56:48 +03:00 committed by GitHub
commit 79571aa67c
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -37,7 +37,7 @@ def act_quant_kernel(x_ptr, y_ptr, s_ptr, BLOCK_SIZE: tl.constexpr, scale_fmt: t
def act_quant(x: torch.Tensor, block_size: int = 128, scale_fmt: Optional[str] = None) -> Tuple[torch.Tensor, torch.Tensor]:
"""
Quantizes the input tensor `x` using block-wise quantization.
Quantizes the input tensor `x` using block-wise quantization as implemented in the given function.
Args:
x (torch.Tensor): The input tensor to be quantized. Must be contiguous and its last dimension size must be divisible by `block_size`.