This repository is the source of truth for official srt-slurm sweep configurations across node counts, models, GPU platforms, and inference frameworks.
The upstream tool is NVIDIA/srt-slurm. Keep benchmark execution logic in that project; keep reusable sweep configuration in this repository.
Recipes are organized by benchmark shape:
recipes/
single-node/
<model>/
<gpu>/
<framework>/
multi-node/
<model>/
<gpu>/
<framework>/
Each leaf directory is reserved for one or more *.yaml sweep configs for that exact combination.
Current recipes:
Run python scripts/update_recipe_table.py after adding or removing recipe directories.
The same check is available as a pre-commit hook at .githooks/pre-commit.
Enable it for a checkout with scripts/install_hooks.sh.
Legend:
- ✅ Recipe is present (links to containing directory)
⚠️ Recipe is in progress- ➖ Not supported (does not fit a single node — use the multi-node recipe, not on InferenceX)
| Model | GB200 / GB300 |
B200 / B300 |
H100 / H200 |
|---|---|---|---|
DeepSeek-R1 |
✅ | ✅ | ✅ |
DeepSeek-V4-Pro |
✅ | ✅ | ✅ |
GLM-5 |
✅ | ➖ | ➖ |
gpt-oss-120b |
✅ | ➖ | ➖ |
Kimi-K2.5 |
✅ | ➖ | ➖ |
MiniMax-M2.5 |
✅ | ✅ | ➖ |
MiniMax-M3 |
✅ | ➖ | ➖ |
| Model | B200 / B300 |
H100 / H200 |
|---|---|---|
DeepSeek-R1 |
✅ | ✅ |
DeepSeek-V4-Pro |
✅ | ✅ |
gpt-oss-120b |
✅ | ✅ |
Kimi-K2.5 |
✅ | ✅ |
MiniMax-M2.5 |
✅ | ✅ |
MiniMax-M3 |
✅ | |
NVIDIA-Nemotron-3-Super-120B-A12B |
✅ NVFP4 | ✅ FP8 |
NVIDIA-Nemotron-3-Ultra |
✅ | ✅ |
Qwen3.5 |
✅ | ✅ |
Install srt-slurm from upstream, then point srtctl at a recipe YAML in this repo:
git clone https://github.com/NVIDIA/srt-slurm.git
cd srt-slurm
uv pip install -e .
RECIPES_PATH=/path/to/srt-slurm-recipes
FRAMEWORK=<framework>
uv run srtctl dry-run -f "${RECIPES_PATH}/recipes/single-node/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4/B200/${FRAMEWORK}/1k1k.yaml"
uv run srtctl apply -f "${RECIPES_PATH}/recipes/single-node/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4/B200/${FRAMEWORK}/1k1k.yaml" \
--tags official,NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4,B200,"${FRAMEWORK}"The dry-run command should be used before submitting jobs.
See CONTRIBUTING.md for how to add or update official sweep recipes.
- Support level: Maintained - see SUPPORT.md for how to get help.
- Security: Report vulnerabilities privately per SECURITY.md. Do not file public issues for security reports.
- Code of Conduct: CODE_OF_CONDUCT.md
- Governance & Maintainers: GOVERNANCE.md · MAINTAINERS.md
- Citation: CITATION.md
This repository follows the upstream srt-slurm license. See LICENSE.