Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
@@ -8,7 +8,6 @@
|
||||
# Copyright (c) 2023-2025, Songlin Yang, Yu Zhang
|
||||
# ruff: noqa: E501
|
||||
import warnings
|
||||
from typing import Optional
|
||||
|
||||
import torch
|
||||
from einops import rearrange
|
||||
@@ -32,7 +31,7 @@ def chunk_gated_delta_rule_fwd(
|
||||
scale: float,
|
||||
initial_state: torch.Tensor,
|
||||
output_final_state: bool,
|
||||
cu_seqlens: Optional[torch.LongTensor] = None,
|
||||
cu_seqlens: torch.LongTensor | None = None,
|
||||
):
|
||||
g = chunk_local_cumsum(g, chunk_size=64, cu_seqlens=cu_seqlens)
|
||||
# obtain WY representation. u is actually the new v.
|
||||
@@ -86,7 +85,7 @@ class ChunkGatedDeltaRuleFunction(torch.autograd.Function):
|
||||
scale: float,
|
||||
initial_state: torch.Tensor,
|
||||
output_final_state: bool,
|
||||
cu_seqlens: Optional[torch.LongTensor] = None,
|
||||
cu_seqlens: torch.LongTensor | None = None,
|
||||
use_qk_l2norm_in_kernel: bool = False,
|
||||
):
|
||||
if use_qk_l2norm_in_kernel:
|
||||
@@ -119,7 +118,7 @@ def chunk_gated_delta_rule(
|
||||
scale: float = None,
|
||||
initial_state: torch.Tensor = None,
|
||||
output_final_state: bool = False,
|
||||
cu_seqlens: Optional[torch.LongTensor] = None,
|
||||
cu_seqlens: torch.LongTensor | None = None,
|
||||
head_first: bool = False,
|
||||
use_qk_l2norm_in_kernel: bool = False,
|
||||
):
|
||||
|
||||
Reference in New Issue
Block a user