20231088/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[Hardware][AWS] update neuron to 2.20 (#8676)

Browse Source 
Signed-off-by: omrishiv <327609+omrishiv@users.noreply.github.com>
This commit is contained in:
omrishiv 2024-09-20 15:19:44 -07:00 committed by GitHub
parent 7c8566aa4f
commit 7f9c8902e3
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
Dockerfile.neuron
View File

@ -1,5 +1,5 @@
# default base image # default base image
ARG BASE_IMAGE="public.ecr.aws/neuron/pytorch-inference-neuronx:2.1.2-neuronx-py310-sdk2.19.1-ubuntu20.04" ARG BASE_IMAGE="public.ecr.aws/neuron/pytorch-inference-neuronx:2.1.2-neuronx-py310-sdk2.20.0-ubuntu20.04"
FROM $BASE_IMAGE FROM $BASE_IMAGE
@ -20,7 +20,7 @@ RUN python3 -m pip install --upgrade pip
RUN python3 -m pip install --no-cache-dir fastapi ninja tokenizers pandas RUN python3 -m pip install --no-cache-dir fastapi ninja tokenizers pandas
RUN python3 -m pip install sentencepiece transformers==4.36.2 -U RUN python3 -m pip install sentencepiece transformers==4.36.2 -U
RUN python3 -m pip install transformers-neuronx --extra-index-url=https://pip.repos.neuron.amazonaws.com -U RUN python3 -m pip install transformers-neuronx --extra-index-url=https://pip.repos.neuron.amazonaws.com -U
RUN python3 -m pip install --pre neuronx-cc==2.12.* --extra-index-url=https://pip.repos.neuron.amazonaws.com -U RUN python3 -m pip install --pre neuronx-cc==2.15.* --extra-index-url=https://pip.repos.neuron.amazonaws.com -U
COPY ./vllm /app/vllm/vllm COPY ./vllm /app/vllm/vllm
COPY ./setup.py /app/vllm/setup.py COPY ./setup.py /app/vllm/setup.py

4
requirements-neuron.txt
View File

@ -2,6 +2,6 @@
-r requirements-common.txt -r requirements-common.txt
# Dependencies for Neuron devices # Dependencies for Neuron devices
transformers-neuronx >= 0.9.0 transformers-neuronx >= 0.12.0
torch-neuronx >= 2.1.0 torch-neuronx >= 2.1.2
neuronx-cc neuronx-cc