mirror of
https://github.com/ml-explore/mlx-examples.git
synced 2025-09-01 12:49:50 +08:00
More cache improvements (#1015)
* fix rotating kv cache for chat use case * reorg + fixes to caching, unify prompt caching across types and use cases for e.g. caching during a chat * nit in chat * fix tests * fix tests * fix tests * docs * chat command * comments + docs * Define meta_state on all Cache implementations * fixes + trim_prompt_cache api * fix default model --------- Co-authored-by: Angelos Katharopoulos <a_katharopoulos@apple.com>
This commit is contained in:
@@ -1,12 +1,12 @@
|
||||
# Copyright © 2023-2024 Apple Inc.
|
||||
|
||||
from dataclasses import dataclass
|
||||
from typing import Dict, List, Optional, Tuple, Union
|
||||
from typing import Any, Dict, List, Optional, Tuple, Union
|
||||
|
||||
import mlx.core as mx
|
||||
import mlx.nn as nn
|
||||
|
||||
from .base import BaseModelArgs, KVCache, create_attention_mask
|
||||
from .base import BaseModelArgs, create_attention_mask
|
||||
from .su_rope import SuScaledRotaryEmbedding
|
||||
|
||||
|
||||
@@ -84,7 +84,7 @@ class Attention(nn.Module):
|
||||
self,
|
||||
x: mx.array,
|
||||
mask: Optional[mx.array] = None,
|
||||
cache: Optional[KVCache] = None,
|
||||
cache: Optional[Any] = None,
|
||||
) -> mx.array:
|
||||
B, L, D = x.shape
|
||||
|
||||
@@ -143,7 +143,7 @@ class TransformerBlock(nn.Module):
|
||||
self,
|
||||
x: mx.array,
|
||||
mask: Optional[mx.array] = None,
|
||||
cache: Optional[KVCache] = None,
|
||||
cache: Optional[Any] = None,
|
||||
) -> mx.array:
|
||||
r = self.self_attn(self.input_layernorm(x), mask, cache)
|
||||
h = x + r
|
||||
@@ -202,11 +202,3 @@ class Model(nn.Module):
|
||||
@property
|
||||
def layers(self):
|
||||
return self.model.layers
|
||||
|
||||
@property
|
||||
def head_dim(self):
|
||||
return self.args.hidden_size // self.args.num_attention_heads
|
||||
|
||||
@property
|
||||
def n_kv_heads(self):
|
||||
return self.args.num_key_value_heads
|
||||
|
Reference in New Issue
Block a user