Skip to content

fix(launcher): use the schema's draft_model global var #2232

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
h-guo18 wants to merge 1 commit into from
+5 −5
Closed

fix(launcher): use the schema's draft_model global var #2232

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
6 changes: 3 additions & 3 deletions tools/launcher/examples/moonshotai/Kimi-K2.5/specdec_bench.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,13 +32,13 @@ pipeline:

global_vars:
hf_model: /hf-local/nvidia/Kimi-K2.5-NVFP4
# Trained+exported DFLASH draft; override: pipeline.global_vars.draft_model_dir=<path>
draft_model_dir: /hf-local/nvidia/Kimi-K2.5-DFlash
# Trained+exported DFLASH draft; override: pipeline.global_vars.draft_model=<path>
draft_model: /hf-local/nvidia/Kimi-K2.5-DFlash

task_0:
script: common/specdec_bench/run.sh
args:
- --draft_model_dir <<global_vars.draft_model_dir>>
- --draft_model_dir <<global_vars.draft_model>>
- --speculative_algorithm DFLASH
- --engine VLLM
- --mtbench /hf-local/HuggingFaceH4/mt_bench_prompts/raw/question.jsonl
Expand Down
4 changes: 2 additions & 2 deletions ...ples/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16/hf_streaming_dspark_warmstart.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,7 +56,7 @@ pipeline:
# config.json layer-type vocabulary already patched for tf5 (see header).
hf_model: /hf-local/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
# The published drafter the warm start continues from.
drafter: /hf-local/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16-DSpark
draft_model: /hf-local/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16-DSpark

# Build /scratchspace/data/train.jsonl. Point data.data_path at the full
# Spec-Decoding-Dataset-v2 corpus to reproduce; eagle_utils also accepts a
Expand All @@ -80,7 +80,7 @@ pipeline:
# causal attention and attention sink all come from this recipe — see header.
- --config modules/Model-Optimizer/modelopt_recipes/huggingface/models/nvidia/Nemotron-3.5-Lightning-30B-A3B-BF16/speculative_decoding/dspark_warmstart.yaml
- model.model_name_or_path=<<global_vars.hf_model>>
- dflash.dflash_init_checkpoint=<<global_vars.drafter>>
- dflash.dflash_init_checkpoint=<<global_vars.draft_model>>
- data.data_path=/scratchspace/data/train.jsonl
# The stock Nemotron template has no {% generation %} tags; without a tagged copy
# answer_only_loss trains on an all-zero mask (see header).
Expand Down
Loading