Skip to content
Draft
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
35 changes: 35 additions & 0 deletions tools/launcher/examples/Qwen/qwen3-v0353a-eagle3/step2_hidden.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,35 @@
# Step 2 hidden-state dump for qwen3-v0353a-eagle3.
#
# Standalone task that dumps hidden states from the target model.
# Output is written to /scratchspace/offline_hidden_states for consumption
# by the downstream EAGLE3 training step.
#
# Usage:
# uv run slurm.py --yaml modules/Model-Optimizer/tools/launcher/examples/Qwen/qwen3-v0353a-eagle3/step2_hidden.yaml --dry-run

job_name: qwen3-v0353a-eagle3_EAGLE3_hidden_dump
pipeline:
allow_to_fail: false
skip: false
note:

global_vars:
hf_model: /hf-local/Qwen/qwen3-v0353a-eagle3

# Step 2: Dump hidden states from target model
task_0:
script: common/eagle3/dump_offline_data.sh
args:
- --input-data /scratchspace/data
- --output-dir /scratchspace/offline_hidden_states
- --max-seq-len 8192
- --tp 8
- --moe-ep 8
environment:
- HF_MODEL_CKPT: <<global_vars.hf_model>>
slurm_config:
_factory_: "slurm_factory"
nodes: 1
ntasks_per_node: 8
gpus_per_node: 8
container: nvcr.io/nvidia/tensorrt-llm/release:1.2.0
Loading