zhangyiss/mlx-examples
1
0
Fork 0
mirror of https://github.com/ml-explore/mlx-examples.git synced 2025-09-01 04:14:38 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Correct the type annotation of cache in llama.py (#828)

Browse Source 
* Update

* Fix isort
This commit is contained in:
Yi Wang
2024-06-10 15:18:34 -07:00
committed by GitHub
parent bb8227f181
commit a54dfd698e
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
llms/mlx_lm/models/llama.py
View File

@@ -4,7 +4,7 @@ from typing import Dict, Optional, Tuple, Union
import mlx.core as mx
import mlx.nn as nn
from .base import BaseModelArgs, create_additive_causal_mask
from .base import BaseModelArgs, KVCache, create_additive_causal_mask
@dataclass
@@ -73,7 +73,7 @@ class Attention(nn.Module):
self,
x: mx.array,
mask: Optional[mx.array] = None,
cache: Optional[Tuple[mx.array, mx.array]] = None,
cache: Optional[KVCache] = None,
) -> mx.array:
B, L, D = x.shape
@@ -135,7 +135,7 @@ class TransformerBlock(nn.Module):
self,
x: mx.array,
mask: Optional[mx.array] = None,
cache: Optional[Tuple[mx.array, mx.array]] = None,
cache: Optional[KVCache] = None,
) -> mx.array:
r = self.self_attn(self.input_layernorm(x), mask, cache)
h = x + r