Update README.md
Browse filesRemoving 2.16 language
README.md
CHANGED
@@ -28,26 +28,15 @@ Please refer to the 🤗 `optimum-neuron` [documentation](https://huggingface.co
|
|
28 |
## Set up the environment
|
29 |
|
30 |
First, use the [DLAMI image from Hugging Face](https://aws.amazon.com/marketplace/pp/prodview-gr3e6yiscria2). It has most of the utilities and drivers preinstalled, but hasn't been updated to 2.16 as of 1/13/24.
|
31 |
-
However, you will need version 2.16 to use these binaries. 2.16 shows a significant performance increase over 2.15 for Llama based models.
|
32 |
|
33 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
34 |
|
35 |
-
```
|
36 |
-
sudo apt-get update -y \
|
37 |
-
&& sudo apt-get install -y --no-install-recommends \
|
38 |
-
aws-neuronx-dkms=2.15.9.0 \
|
39 |
-
aws-neuronx-collectives=2.19.7.0-530fb3064 \
|
40 |
-
aws-neuronx-runtime-lib=2.19.5.0-97e2d271b \
|
41 |
-
aws-neuronx-tools=2.16.1.0
|
42 |
-
|
43 |
-
pip3 install --upgrade \
|
44 |
-
neuronx-cc==2.12.54.0 \
|
45 |
-
torch-neuronx==1.13.1.1.13.0 \
|
46 |
-
transformers-neuronx==0.9.474 \
|
47 |
-
--extra-index-url=https://pip.repos.neuron.amazonaws.com
|
48 |
-
|
49 |
-
pip3 install git+https://github.com/huggingface/optimum-neuron.git
|
50 |
-
```
|
51 |
## Running inference from this repository
|
52 |
|
53 |
|
|
|
28 |
## Set up the environment
|
29 |
|
30 |
First, use the [DLAMI image from Hugging Face](https://aws.amazon.com/marketplace/pp/prodview-gr3e6yiscria2). It has most of the utilities and drivers preinstalled, but hasn't been updated to 2.16 as of 1/13/24.
|
|
|
31 |
|
32 |
+
(As of the 20240123 version, the Hugging Face DLAMI image has the updated 2.16 binaries)
|
33 |
+
|
34 |
+
~~However, you will need version 2.16 to use these binaries. 2.16 shows a significant performance increase over 2.15 for Llama based models.~~
|
35 |
+
|
36 |
+
~~The commands below will update your 2.15 libraries to 2.16.~~
|
37 |
+
|
38 |
+
```<update commands removed>```
|
39 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
40 |
## Running inference from this repository
|
41 |
|
42 |
|