Reduce Docker size by removing duplicate torch install (#144)

Dockerfile

@@ -208,7 +208,7 @@ COPY server/Makefile server/Makefile
 
 RUN cd server && \
     make gen-server && \
-    pip install ".[bnb, accelerate, quantize]" --no-cache-dir
+    pip install ".[bnb, accelerate, quantize, peft]" --no-cache-dir
 
 # Install router
 COPY --from=builder /usr/src/target/release/lorax-router /usr/local/bin/lorax-router
@@ -234,7 +234,8 @@ RUN chmod +x sync.sh
 
 RUN curl "https://awscli.amazonaws.com/awscli-exe-linux-x86_64.zip" -o "awscliv2.zip" && \
     unzip awscliv2.zip && \
-    sudo ./aws/install
+    sudo ./aws/install && \
+    rm -rf aws awscliv2.zip
 
 # ENTRYPOINT ["./entrypoint.sh"]
 ENTRYPOINT ["lorax-launcher"]

server/Makefile

@@ -15,14 +15,10 @@ gen-server:
 	find lorax_server/pb/ -type f -name "*.py" -print0 -exec sed -i -e 's/^\(import.*pb2\)/from . \1/g' {} \;
 	touch lorax_server/pb/__init__.py
 
-install-torch:
-	# Install specific version of torch
-	pip install torch --extra-index-url https://download.pytorch.org/whl/cu118 --no-cache-dir
-
-install: gen-server install-torch
+install: gen-server
 	pip install pip --upgrade
 	pip install -r requirements.txt
-	pip install -e ".[bnb, accelerate]"
+	pip install -e ".[bnb, accelerate, quantize, peft]"
 
 run-dev:
 	# SAFETENSORS_FAST_GPU=1 python -m torch.distributed.run --nproc_per_node=1 lorax_server/cli.py serve gpt2
@@ -32,4 +28,4 @@ run-dev:
 	# SAFETENSORS_FAST_GPU=1 python -m torch.distributed.run --nproc_per_node=1 lorax_server/cli.py serve flozi00/Mistral-7B-german-assistant-v5-4bit-autogptq --quantize gptq
 
 export-requirements:
-	poetry export -o requirements.txt -E bnb -E quantize --without-hashes
+	poetry export -o requirements.txt -E bnb --without-hashes