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

Quantized KV Cache (#1075)

Browse Source 
* add QuantizedKVCache

* simplify

* add tests

* single sdpa function

* fix sed

* in place

* fix tests

* support different k and v head dims
This commit is contained in:
Alex Barron
2024-10-31 16:59:52 -07:00
committed by GitHub
parent 9f34fdbda4
commit 85ffd2c96a
32 changed files with 411 additions and 85 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
llms/mlx_lm/models/qwen2_moe.py
View File

@@ -7,7 +7,7 @@ from typing import Any, Dict, Optional, Union
import mlx.core as mx
import mlx.nn as nn
from .base import BaseModelArgs, create_attention_mask
from .base import BaseModelArgs, create_attention_mask, scaled_dot_product_attention
from .switch_layers import SwitchGLU
@@ -89,8 +89,8 @@ class Attention(nn.Module):
queries = self.rope(queries)
keys = self.rope(keys)
output = mx.fast.scaled_dot_product_attention(
queries, keys, values, scale=self.scale, mask=mask
output = scaled_dot_product_attention(
queries, keys, values, cache=cache, scale=self.scale, mask=mask
)
output = output.transpose(0, 2, 1, 3).reshape(B, L, -1)
return self.o_proj(output)