Feature: k2_horizon_uno decode is about 20% slower than needed (no CUDA graph; LoRA branch computed on rows whose mask is 0)

Abierto
  • ¿Algo no está bien?
#2,054 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
cpp, python, pytorch
Área
backend, machine-learning, performance

Línea de trabajo

Read families/k2_horizon_uno/README.md, especially section 7, then trace the Uno native runtime and engine profiles used by the k2-horizon-7b-uno manifest in linear_spec_lora mode. Investigate CUDA graph replay for each supported row count and how prompt and verify calls can use an engine without LoRA. Done means both changes are measured against the reported bf16 baselines and decoding behavior is checked for regressions.

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/k2_horizon_uno runs speculative decoding with one dynamic engine that takes 1 to 8 rows per call and a per-row LoRA mask (draft rows mask 1; prompt and verify rows mask 0). Two costs on main, found during the FP8 study recorded in families/k2_horizon_uno/README.md (#2039, section 7):

  1. The Uno native runtime never enables CUDA graphs. A bf16 8-row call launches about 830 kernels; the host loop spends about 6 ms per 8-row call against 5.3 to 5.7 ms when the same call is replayed as a CUDA graph.
  2. The LoRA branch is computed for every row of every call, including prompt and verify calls whose mask is all 0. The branch (rank 128 on all 7 projections, in bf16) is 19% to 23% of a call: the bf16 engine without the branch is 1.21x to 1.24x faster.

Both are larger than what FP8 gives on this family (FP8 was measured and not shipped, see the README).

Proposed outcome

  1. Replay the decode calls as CUDA graphs in the Uno native runtime (per row count used).
  2. Skip the LoRA branch when the mask of a call is all 0, for example with a second engine profile (or engine) without LoRA for prompt and verify calls.

Model and target details

IFM/K2-Horizon-7B-Uno @ ec92bbd768f4a404319625204544782e3377bcd7 (the k2-horizon-7b-uno manifest, linear_spec_lora mode) on the K2-Horizon-7B base; bf16; TensorRT 11.4; B200 / B300; max_sequence_length 1024.

Alternatives considered

FP8 of the base projections (measured, not shipped): the 8-row call is 0.96x (B200) and 0.88x (B300) of bf16 without a CUDA graph, because the bf16 LoRA branch and the kernel count stay.

Additional context

The same study found that speculative decode equals the engine's own greedy autoregressive output on 13 of 14 prompts only (bf16): 8-row and 1-row calls differ in the last bits, which changes the argmax at near ties.

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.