Add known_issue about container oom (#104)

* add known_issue

* update

Author: hzjane

vllm/KNOWN_ISSUES.md

@@ -11,3 +11,15 @@ When using a single GPU card over a x16 PCIe connection without a PCIe switch, t
 Workaround: Change the PCIe slot configuration in BIOS from Auto/x16 to x8/x8.
 With this change, over 40 GB/s bi-directional P2P bandwidth can be achieved.
 Root cause analysis is still in progress.
+
+# 03. Container OOM killed by using `--enable-auto-tool-choice` and starting container not by /bin/bash and not run `source /opt/intel/oneapi/setvars.sh`
+
+When using `--enable-auto-tool-choice` and deploy container by docker-compose without `source /opt/intel/oneapi/setvars.sh`, the LD_LIBRARY_PATH will be different and cause the container OOM. It can be reproduced by this two command:
+
+```bash
+docker run --rm  --entrypoint "/bin/bash" --name=test intel/llm-scaler-vllm:latest -c env | grep LD_LIBRARY_PATH
+ 
+docker run --rm --entrypoint "/bin/bash" --name=test intel/llm-scaler-vllm:latest -c "source /opt/intel/oneapi/setvars.sh --force && env | grep LD_LIBRARY_PATH"
+```
+
+So we need to run `source /opt/intel/oneapi/setvars.sh --force` to ensure some configurations are consistent.