From 37f0b41ac6501266a661ebda3b1eff7bea9f3a1b Mon Sep 17 00:00:00 2001 From: Arupm <146566355+arupm23@users.noreply.github.com> Date: Wed, 7 May 2025 19:26:51 -0400 Subject: [PATCH] Update kernel.py --- inference/kernel.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/inference/kernel.py b/inference/kernel.py index ba18dca..8910f83 100644 --- a/inference/kernel.py +++ b/inference/kernel.py @@ -32,7 +32,7 @@ def act_quant_kernel(x_ptr, y_ptr, s_ptr, BLOCK_SIZE: tl.constexpr): def act_quant(x: torch.Tensor, block_size: int = 128) -> 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`.