From d6c8e9d2b6001b5c0cbbbde62963d1bbe1eb0a89 Mon Sep 17 00:00:00 2001 From: Keval Morabia <28916987+kevalmorabia97@users.noreply.github.com> Date: Wed, 1 Apr 2026 17:53:20 +0530 Subject: [PATCH] Remove internal lustre paths (#1148) Remove internal /lusre paths ## Summary by CodeRabbit * **Configuration Updates** * Set a concrete default container image to an NVIDIA PyTorch container for templates. * Removed built-in default values in scripts; key environment/config variables must be provided externally. * Replaced absolute example paths with placeholder relative paths and TODO notes requiring user customization. --------- Signed-off-by: Keval Morabia <28916987+kevalmorabia97@users.noreply.github.com> --- .../qwen3-30b-a3b-instruct-2507-moe_template.conf | 2 +- examples/llm_qad/configs/qwen3-8b_template.conf | 2 +- examples/llm_qad/sbatch_qad.sh | 11 ----------- .../torch_onnx/diffusers/qad_example/ltx2_qad.yaml | 6 +++--- 4 files changed, 5 insertions(+), 16 deletions(-) diff --git a/examples/llm_qad/configs/qwen3-30b-a3b-instruct-2507-moe_template.conf b/examples/llm_qad/configs/qwen3-30b-a3b-instruct-2507-moe_template.conf index c30af0f98..6d2c52cc8 100644 --- a/examples/llm_qad/configs/qwen3-30b-a3b-instruct-2507-moe_template.conf +++ b/examples/llm_qad/configs/qwen3-30b-a3b-instruct-2507-moe_template.conf @@ -61,7 +61,7 @@ export DATACACHE_DIR="" # path to data cache directory ######################################################## # CONTAINER ######################################################## -export CONTAINER_IMAGE="" # path to container image, e.g., nvcr.io/nvidia/pytorch:26.01-py3 +export CONTAINER_IMAGE="nvcr.io/nvidia/pytorch:26.01-py3" # path to container image or .sqsh file export CONTAINER_MOUNTS="" # container mounts, e.g., "/lustre/fs1:/lustre/fs1" export CONTAINER_WORKDIR="" # container work directory, e.g., "/Model-Optimizer/examples/llm_qad" diff --git a/examples/llm_qad/configs/qwen3-8b_template.conf b/examples/llm_qad/configs/qwen3-8b_template.conf index 0def8dc8c..24beec5d6 100644 --- a/examples/llm_qad/configs/qwen3-8b_template.conf +++ b/examples/llm_qad/configs/qwen3-8b_template.conf @@ -59,7 +59,7 @@ export DATACACHE_DIR="" # path to data cache directory ######################################################## # CONTAINER ######################################################## -export CONTAINER_IMAGE="" # path to container image, e.g., nvcr.io/nvidia/pytorch:26.01-py3 +export CONTAINER_IMAGE="nvcr.io/nvidia/pytorch:26.01-py3" # path to container image or .sqsh file export CONTAINER_MOUNTS="" # container mounts, e.g., "/lustre/fs1:/lustre/fs1" export CONTAINER_WORKDIR="" # container work directory diff --git a/examples/llm_qad/sbatch_qad.sh b/examples/llm_qad/sbatch_qad.sh index 613b9bc27..7ecc01281 100755 --- a/examples/llm_qad/sbatch_qad.sh +++ b/examples/llm_qad/sbatch_qad.sh @@ -58,19 +58,8 @@ if [[ -n "$CONFIG_FILE" ]]; then fi fi -# === Default Paths (override in config) === -MLM_DIR="${MLM_DIR:-/lustre/fs1/portfolios/coreai/projects/coreai_dlalgo_modelopt/users/weimingc/workspace/Megatron-LM}" -MODELOPT_DIR="${MODELOPT_DIR:-/lustre/fs1/portfolios/coreai/projects/coreai_dlalgo_modelopt/users/weimingc/workspace/TensorRT-Model-Optimizer}" -MODELS_ROOT="${MODELS_ROOT:-/lustre/fs1/portfolios/coreai/projects/coreai_dlalgo_modelopt/users/weimingc/models}" -QAD_CHECKPOINT_ROOT="${QAD_CHECKPOINT_ROOT:-/lustre/fs1/portfolios/coreai/projects/coreai_dlalgo_modelopt/users/weimingc/checkpoints}" -DATACACHE_DIR="${DATACACHE_DIR:-/lustre/fs1/portfolios/coreai/projects/coreai_dlalgo_modelopt/users/weimingc/data_cache}" LOG_DIR="${LOG_DIR:-${QAD_CHECKPOINT_ROOT}/logs_slurm}" -# Container settings -CONTAINER_IMAGE="${CONTAINER_IMAGE:-/lustre/fs1/portfolios/coreai/projects/coreai_dlalgo_modelopt/users/weimingc/containers/pytorch_25.06-py3.sqsh}" -CONTAINER_MOUNTS="${CONTAINER_MOUNTS:-/lustre/fs1:/lustre/fs1}" -CONTAINER_WORKDIR="${CONTAINER_WORKDIR:-/lustre/fs1/portfolios/coreai/projects/coreai_dlalgo_modelopt/users/weimingc/workspace/TensorRT-Model-Optimizer/examples/llm_qad}" - # Parallelism (required from config) TP_SIZE="${TP_SIZE:?ERROR: TP_SIZE must be set in config}" MBS="${MBS:?ERROR: MBS must be set in config}" diff --git a/examples/windows/torch_onnx/diffusers/qad_example/ltx2_qad.yaml b/examples/windows/torch_onnx/diffusers/qad_example/ltx2_qad.yaml index da6e5d74e..1314deb75 100644 --- a/examples/windows/torch_onnx/diffusers/qad_example/ltx2_qad.yaml +++ b/examples/windows/torch_onnx/diffusers/qad_example/ltx2_qad.yaml @@ -1,9 +1,9 @@ # LTX-2 QAD Training Configuration model: - model_path: "/lustre/fsw/portfolios/adlr/projects/adlr_psx_numerics/users/ynankani/ComfyUI/models/checkpoints/ltx-av-step-1933500-split-new-vae.safetensors" + model_path: "/path/to/ltx2/checkpoint.safetensors" # TODO: Set your LTX-2 checkpoint path training_mode: "full" load_checkpoint: - text_encoder_path: "/lustre/fsw/portfolios/adlr/users/dhutchins/models/gemma" + text_encoder_path: "/path/to/gemma" # TODO: Set your Gemma text encoder path training_strategy: name: "text_to_video" @@ -26,7 +26,7 @@ acceleration: load_text_encoder_in_8bit: true data: - preprocessed_data_root: "/lustre/fsw/portfolios/adlr/users/scavallari/ltx-qad/qad-dataset" + preprocessed_data_root: "/path/to/preprocessed" # TODO: Set your preprocessed dataset path num_dataloader_workers: 2 validation: