Skip to content

Commit d6c8e9d

Browse files
Remove internal lustre paths (#1148)
Remove internal /lusre paths <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## 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. <!-- end of auto-generated comment: release notes by coderabbit.ai --> --------- Signed-off-by: Keval Morabia <28916987+kevalmorabia97@users.noreply.github.com>
1 parent c37c74f commit d6c8e9d

4 files changed

Lines changed: 5 additions & 16 deletions

File tree

examples/llm_qad/configs/qwen3-30b-a3b-instruct-2507-moe_template.conf

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -61,7 +61,7 @@ export DATACACHE_DIR="" # path to data cache directory
6161
########################################################
6262
# CONTAINER
6363
########################################################
64-
export CONTAINER_IMAGE="" # path to container image, e.g., nvcr.io/nvidia/pytorch:26.01-py3
64+
export CONTAINER_IMAGE="nvcr.io/nvidia/pytorch:26.01-py3" # path to container image or .sqsh file
6565
export CONTAINER_MOUNTS="" # container mounts, e.g., "/lustre/fs1:/lustre/fs1"
6666
export CONTAINER_WORKDIR="" # container work directory, e.g., "<path-to-modelopt>/Model-Optimizer/examples/llm_qad"
6767

examples/llm_qad/configs/qwen3-8b_template.conf

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -59,7 +59,7 @@ export DATACACHE_DIR="" # path to data cache directory
5959
########################################################
6060
# CONTAINER
6161
########################################################
62-
export CONTAINER_IMAGE="" # path to container image, e.g., nvcr.io/nvidia/pytorch:26.01-py3
62+
export CONTAINER_IMAGE="nvcr.io/nvidia/pytorch:26.01-py3" # path to container image or .sqsh file
6363
export CONTAINER_MOUNTS="" # container mounts, e.g., "/lustre/fs1:/lustre/fs1"
6464
export CONTAINER_WORKDIR="" # container work directory
6565

examples/llm_qad/sbatch_qad.sh

Lines changed: 0 additions & 11 deletions
Original file line numberDiff line numberDiff line change
@@ -58,19 +58,8 @@ if [[ -n "$CONFIG_FILE" ]]; then
5858
fi
5959
fi
6060

61-
# === Default Paths (override in config) ===
62-
MLM_DIR="${MLM_DIR:-/lustre/fs1/portfolios/coreai/projects/coreai_dlalgo_modelopt/users/weimingc/workspace/Megatron-LM}"
63-
MODELOPT_DIR="${MODELOPT_DIR:-/lustre/fs1/portfolios/coreai/projects/coreai_dlalgo_modelopt/users/weimingc/workspace/TensorRT-Model-Optimizer}"
64-
MODELS_ROOT="${MODELS_ROOT:-/lustre/fs1/portfolios/coreai/projects/coreai_dlalgo_modelopt/users/weimingc/models}"
65-
QAD_CHECKPOINT_ROOT="${QAD_CHECKPOINT_ROOT:-/lustre/fs1/portfolios/coreai/projects/coreai_dlalgo_modelopt/users/weimingc/checkpoints}"
66-
DATACACHE_DIR="${DATACACHE_DIR:-/lustre/fs1/portfolios/coreai/projects/coreai_dlalgo_modelopt/users/weimingc/data_cache}"
6761
LOG_DIR="${LOG_DIR:-${QAD_CHECKPOINT_ROOT}/logs_slurm}"
6862

69-
# Container settings
70-
CONTAINER_IMAGE="${CONTAINER_IMAGE:-/lustre/fs1/portfolios/coreai/projects/coreai_dlalgo_modelopt/users/weimingc/containers/pytorch_25.06-py3.sqsh}"
71-
CONTAINER_MOUNTS="${CONTAINER_MOUNTS:-/lustre/fs1:/lustre/fs1}"
72-
CONTAINER_WORKDIR="${CONTAINER_WORKDIR:-/lustre/fs1/portfolios/coreai/projects/coreai_dlalgo_modelopt/users/weimingc/workspace/TensorRT-Model-Optimizer/examples/llm_qad}"
73-
7463
# Parallelism (required from config)
7564
TP_SIZE="${TP_SIZE:?ERROR: TP_SIZE must be set in config}"
7665
MBS="${MBS:?ERROR: MBS must be set in config}"

examples/windows/torch_onnx/diffusers/qad_example/ltx2_qad.yaml

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -1,9 +1,9 @@
11
# LTX-2 QAD Training Configuration
22
model:
3-
model_path: "/lustre/fsw/portfolios/adlr/projects/adlr_psx_numerics/users/ynankani/ComfyUI/models/checkpoints/ltx-av-step-1933500-split-new-vae.safetensors"
3+
model_path: "/path/to/ltx2/checkpoint.safetensors" # TODO: Set your LTX-2 checkpoint path
44
training_mode: "full"
55
load_checkpoint:
6-
text_encoder_path: "/lustre/fsw/portfolios/adlr/users/dhutchins/models/gemma"
6+
text_encoder_path: "/path/to/gemma" # TODO: Set your Gemma text encoder path
77

88
training_strategy:
99
name: "text_to_video"
@@ -26,7 +26,7 @@ acceleration:
2626
load_text_encoder_in_8bit: true
2727

2828
data:
29-
preprocessed_data_root: "/lustre/fsw/portfolios/adlr/users/scavallari/ltx-qad/qad-dataset"
29+
preprocessed_data_root: "/path/to/preprocessed" # TODO: Set your preprocessed dataset path
3030
num_dataloader_workers: 2
3131

3232
validation:

0 commit comments

Comments
 (0)