Update fmi to inference package version 0.2.9 (#3334)

* Update to fmi 0.2.9

* minor update

assets/training/model_management/environments/foundation-model-inference/context/Dockerfile

@@ -47,11 +47,7 @@ RUN pip install git+https://github.com/stanford-futuredata/megablocks.git@5897cd
 # RUN pip install -e ./ --no-cache-dir
 
 # When copied to assets repo, change to install from public pypi
-RUN pip install llm-optimized-inference==0.2.8 --no-cache-dir
-
-RUN pip uninstall -y vllm
-RUN pip uninstall transformers -y
-RUN pip install https://automlsamplenotebookdata.blob.core.windows.net/vllm/vllm-0.4.1-cp310-cp310-linux_x86_64.whl
+RUN pip install llm-optimized-inference==0.2.9 --no-cache-dir
 
 # clean conda and pip caches
 RUN rm -rf ~/.cache/pip
@@ -63,4 +59,4 @@ RUN chmod +x /var/runit/api_server/run
 ENV SVDIR=/var/runit
 ENV WORKER_TIMEOUT=3600
 EXPOSE 5001
-CMD [ "runsvdir", "/var/runit" ]
+CMD [ "runsvdir", "/var/runit" ]