Feature: nemotron_omni decode is bound by 2944 conditional expert subgraphs per token (about 50 ms/token for a 3B-active model)

Abierto
  • ¿Algo no está bien?
#2,060 0 comentarios 0 reacciones 0 asignados Ver en GitHub

Los mantenedores suelen responder en 1 día

Nadie ha tomado este issue todavía.

Evaluación

Dificultad
5/5
Tiempo estimado
Más de una semana
Aptitud para principiantes
35/100
Tipo de issue
Nueva funcionalidad
Claridad
Bastante claro
Estado de actividad
Activo
Stack tecnológico
python, pytorch
Área
machine-learning

Línea de trabajo

Start with families/nemotron_omni/moe.py and inspect how each routed expert is built as an IIfConditional subgraph. Compare this with another family’s gathered MoE implementation, then investigate whether the selected experts’ weights can be run as a grouped or batched GEMM. Done means reducing per-token decode time and decoder plan and build size; the issue gives B200/B300 decode measurements for comparison.

Escrito por el modelo de indexación a partir del texto del issue.

Descripción

enhancement

Request type: Improvement to existing behavior

Problem and use case

families/nemotron_omni builds each MoE layer of the Nemotron-H language model as 128 IIfConditional expert subgraphs (moe.py, one per routed expert; top-6 run). With 23 MoE layers that is 2944 conditional expert subgraphs per decode step, and the decoder plan has about 25k to 64k layers.

On the official NVFP4 checkpoint (the manifests' nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-NVFP4), decode takes about 48 to 53 ms per token on B200 / B300 (about 20 tokens/s), for a model with about 3B active parameters (reading 3B parameters at about 8 TB/s would take well under 1 ms). Prefill is token by token through the same step, so it has the same cost per token.

The step time does not depend on the weight precision, which shows the step is bound by the conditional structure and kernel count, not by weight reads (decoder only, TensorRT 11.4, batch 1, ms per token at cache positions 100 / 2000):

GPU fp16 (from the BF16 checkpoint, built with the family decoder code) FP8 (official FP8 checkpoint) NVFP4 (as on main)
B200 47.7 / 47.8 48.3 / 48.4 49.7 / 49.8
B300 48.9 / 48.8 48.9 / 48.7 49.7 / 49.6

Decoder build time is also large: 24 to 52 minutes on B200 / B300 and about 101 minutes on H100 for NVFP4.

Proposed outcome

Build the routed experts of each MoE layer without one conditional subgraph per expert, for example a gathered/batched expert formulation (gather the selected experts' weights and run them as one grouped or batched GEMM, as other families do with a gathered MoE), so the decode step time scales with the active weights and the plan and build time shrink.

Model and target details

nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-NVFP4 @ 16993199e436da4ba75ddc410855f87e0d996ee6 (the nemotron-omni-nvfp4-native manifest). Language model: 52 layers (23 Mamba2, 23 MoE with 128 routed experts top-6 plus 1 shared, 6 attention), hidden 2688. TensorRT 11.4; B200 / B300 (also seen on H100).

Alternatives considered

FP8 weights (official FP8 checkpoint) and fp16 weights give the same step time as NVFP4 (table above), so weight precision does not help while the MoE stays conditional.

Additional context

Found during an FP8 study of this family (not merged). Separate note for anyone building a Hugging Face reference for Nemotron-H: without mamba-ssm, the checkpoint's own PyTorch fallback in modeling_nemotron_h.py diverges after the first 128-token chunk (KL about 1e-8 on positions 0 to 127, 0.07 to 0.39 after); a plain sequential scan matches the fp16 engine (KL 0.0032).

Lenguaje dominante
Python
Estrellas
288
Forks
73
Merge medio
1 d 3 h
PR fusionados (30 d)
273

Preparar el entorno

Primeros pasos

  1. Lee el issue completo y luego la guía de contribución del proyecto.
  2. Comenta en el issue que vas a ocuparte — evita que dos personas hagan lo mismo.
  3. Haz un fork del repositorio y trabaja en una rama.
  4. Abre un pull request que haga referencia al número del issue.

Más de NVIDIA/TensorRT-Model-Connect

Todos los issues de NVIDIA/TensorRT-Model-Connect

Issues similares

Más issues de Python

Recibe los nuevos issues en tu correo

Un resumen breve de issues de GitHub para principiantes.