image: add fast_moe into fms-hf-tuning image (#512)

Signed-off-by: Will Johnson <[email protected]>

Author: willmj

build/Dockerfile

@@ -154,11 +154,13 @@ RUN --mount=type=cache,target=/home/${USER}/.cache/pip,uid=${USER_UID} \
 # fms_acceleration_peft = PEFT-training, e.g., 4bit QLoRA
 # fms_acceleration_foak = Fused LoRA and triton kernels
 # fms_acceleration_aadp = Padding-Free Flash Attention Computation
+# fms_acceleration_moe = Parallelized Mixture of Experts
 RUN if [[ "${ENABLE_FMS_ACCELERATION}" == "true" ]]; then \
         python -m pip install --user "$(head bdist_name)[fms-accel]"; \
         python -m fms_acceleration.cli install fms_acceleration_peft; \
         python -m fms_acceleration.cli install fms_acceleration_foak; \
         python -m fms_acceleration.cli install fms_acceleration_aadp; \
+        python -m fms_acceleration.cli install fms_acceleration_moe; \
     fi
 
 RUN if [[ "${ENABLE_AIM}" == "true" ]]; then \