Install Marlin from standalone package

Dockerfile

@@ -140,13 +140,6 @@ COPY server/Makefile-eetq Makefile
 # Build specific version of transformers
 RUN TORCH_CUDA_ARCH_LIST="8.0;8.6+PTX" make build-eetq
 
-# Build marlin kernels
-FROM kernel-builder AS marlin-kernels-builder
-WORKDIR /usr/src
-COPY server/marlin/ .
-# Build specific version of transformers
-RUN TORCH_CUDA_ARCH_LIST="8.0;8.6+PTX" python setup.py build
-
 # Build Lorax Punica kernels
 FROM kernel-builder AS lorax-punica-builder
 WORKDIR /usr/src
@@ -231,9 +224,6 @@ COPY --from=exllamav2-kernels-builder /usr/src/build/lib.linux-x86_64-cpython-31
 COPY --from=awq-kernels-builder /usr/src/llm-awq/awq/kernels/build/lib.linux-x86_64-cpython-310 /opt/conda/lib/python3.10/site-packages
 # Copy build artifacts from eetq kernels builder
 COPY --from=eetq-kernels-builder /usr/src/eetq/build/lib.linux-x86_64-cpython-310 /opt/conda/lib/python3.10/site-packages
-# Copy build artifacts from marlin kernels builder
-COPY --from=marlin-kernels-builder /usr/src/build/lib.linux-x86_64-cpython-310 /opt/conda/lib/python3.10/site-packages
-COPY --from=lorax-punica-builder /usr/src/lorax-punica/server/punica_kernels/build/lib.linux-x86_64-cpython-310 /opt/conda/lib/python3.10/site-packages
 # Copy build artifacts from fbgemm builder
 COPY --from=fbgemm-builder /usr/src/fbgemm/fbgemm_gpu/_skbuild/linux-x86_64-3.10/cmake-install /opt/conda/lib/python3.10/site-packages
 # Copy build artifacts from vllm builder
@@ -252,7 +242,7 @@ COPY server/Makefile server/Makefile
 RUN cd server && \
     make gen-server && \
     pip install -r requirements_cuda.txt && \
-    pip install ".[bnb, accelerate, quantize, peft, outlines]" --no-cache-dir && \
+    pip install ".[bnb, accelerate, marlin, quantize, peft, outlines]" --no-cache-dir && \
     pip install nvidia-nccl-cu12==2.22.3
 
 ENV LD_PRELOAD=/opt/conda/lib/python3.10/site-packages/nvidia/nccl/lib/libnccl.so.2