Entrypoint /opt/nvidia/nvidia_entrypoint.sh; WorkingDir /workspace; ExposedPorts 6006/tcp, 8888/tcp

TARGETARCH=amd64

RC_DATE=25.11

com.nvidia.build.ref=e999501d80819a93a628ec5d6f94b4279cc0c175

NVIDIA_BUILD_REF=e999501d80819a93a628ec5d6f94b4279cc0c175

com.nvidia.build.id=237133418

NVIDIA_BUILD_ID=237133418

NVIDIA_BUILD_ID=237133418

/workspace

NVIDIA_BIGNLP_VERSION= UV_VERSION=0.8.22 TRT_VER=10.13.3.9 CUDA_VER=13.0 CUDNN_VER=9.13.1.26-1 NCCL_VER=2.28.3-1+cuda13.0 CUBLAS_VER=13.0.2.14-1 TRT_LLM_COMMIT=55a9771ff0122ded47e6711eaf19c48f54630fe6 TRT_LLM_VERSION= REINSTALL_NSYS=False NSYS_VERSION=2025.4.1.172 REINSTALL_CUDNN=False CUDNN_VERSION=9.13.0.50 REINSTALL_NCCL=False NCCL_VERSION=2.27.7 INSTALL_DEEPEP=True DEEPEP_COMMIT=ef73fd9a4c098e09929e48dfd696505ddc8e2043 TARGET_ARCH=x86 MCORE_REPO=https://github.com/NVIDIA/Megatron-LM.git MCORE_COMMIT=0d8e0714cd29c01e164fe6de9f532182bdffa942 MCORE_VERSION=0.16.0rc0 NEMO_COMMIT=0425500334506b9b9f8dfa554fd7d920746a08cd NEMO_VERSION=2.6.0rc0 NEMO_EXPORT_DEPLOY_COMMIT=d1de8ef50e04e445e0852a62b30b5ce98660464f NEMO_EXPORT_DEPLOY_VERSION= NEMO_EVAL_COMMIT= NEMO_EVAL_VERSION= MEGATRON_BRIDGE_COMMIT=7c7226b2376ed617ae5e83c33b7c6601c50efd56 MEGATRON_BRIDGE_VERSION=0.2.0rc7 INSTALL_RESIL=True RESIL_COMMIT=54f85fe422d296cf04ea524130014bd3a2c3add1 RESIL_VERSION=0.4.1 INSTALL_MODELOPT=True MODELOPT_VERSION=0.37.0 NEMO_RUN_COMMIT=01a9a8ba360f7b2908728ad0516e0ad9d936966d SKIP_TRTLLM=false URM_USER_ACCOUNT=donghyukc PRE_COMPILE_QUANT_KERNELS=True if [ $PRE_COMPILE_QUANT_KERNELS = "True" ]; then python -c "import modelopt.torch.quantization.extensions as ext; ext.precompile()"; fi &&
  python -m ipykernel install --name=python3 --display-name="Python 3 (ipykernel)" &&
  if [ -f /usr/local/bin/torchrun ]; then sed -i '1s|#!/usr/bin/python|#!/usr/bin/env python|' /usr/local/bin/torchrun; fi &&
  mkdir -p /workspace &&
  chmod -R a+w /workspace &&
  URM_API_TOKEN=$(cat /run/secrets/URM_API_TOKEN) &&
  wget --http-user $URM_USER_ACCOUNT --http-password ${URM_API_TOKEN} "https://urm.nvidia.com/artifactory/nemo-fw-generic-local/llama3_70b_tokenizer.tar.gz" &&
  wget --http-user $URM_USER_ACCOUNT --http-password ${URM_API_TOKEN} "https://urm.nvidia.com/artifactory/nemo-fw-generic-local/llama3_8b_tokenizer.tar.gz" &&
  mkdir -p /tmp_assets &&
  mkdir -p ~/.cache/huggingface &&
  tar -xzvf llama3_8b_tokenizer.tar.gz -C /tmp_assets &&
  tar -xzvf llama3_70b_tokenizer.tar.gz -C /tmp_assets &&
  cp -rf /tmp_assets/hub ~/.cache/huggingface &&
  rm -rf /tmp_assets &&
  rm llama3_8b_tokenizer.tar.gz llama3_70b_tokenizer.tar.gz &&
  python -c "from transformers import AutoTokenizer, Qwen2Tokenizer, CLIPImageProcessor; _=AutoTokenizer.from_pretrained('gpt2'); _=AutoTokenizer.from_pretrained('bert-base-cased'); _=AutoTokenizer.from_pretrained('bert-large-cased'); _=AutoTokenizer.from_pretrained('bert-large-uncased'); _=AutoTokenizer.from_pretrained('bigcode/starcoder2-tokenizer'); _=AutoTokenizer.from_pretrained('EleutherAI/gpt-neox-20b'); _=AutoTokenizer.from_pretrained('nvidia/Nemotron-H-8B-Base-8K'); _=AutoTokenizer.from_pretrained('nvidia/Nemotron-H-47B-Base-8K'); _=AutoTokenizer.from_pretrained('nvidia/Nemotron-H-56B-Base-8K'); _=AutoTokenizer.from_pretrained('THUDM/chatglm2-6b',trust_remote_code=True); _=AutoTokenizer.from_pretrained('THUDM/chatglm3-6b',trust_remote_code=True); _=Qwen2Tokenizer.from_pretrained('qwen/Qwen1.5-7B',trust_remote_code=True); _=Qwen2Tokenizer.from_pretrained('qwen/Qwen1.5-14B',trust_remote_code=True); _=AutoTokenizer.from_pretrained('openai/clip-vit-large-patch14'); _=AutoTokenizer.from_pretrained('meta-llama/Meta-Llama-3-8B', local_files_only=True); _=AutoTokenizer.from_pretrained('meta-llama/Meta-Llama-3-70B', local_files_only=True); _=AutoTokenizer.from_pretrained('meta-llama/Meta-Llama-3-8B-instruct', local_files_only=True); _=AutoTokenizer.from_pretrained('meta-llama/Meta-Llama-3-70B-instruct', local_files_only=True); _=CLIPImageProcessor.from_pretrained('openai/clip-vit-large-patch14'); _=CLIPImageProcessor.from_pretrained('openai/clip-vit-large-patch14-336')"