Skip to content

GitLab

Unverified Commit a8213787 authored by Hongkuan Zhou's avatar Hongkuan Zhou Committed by GitHub
Browse files

fix: add sweep range for moe dgdr example (#5225) 


Signed-off-by: default avatarhongkuanz <hongkuanz@nvidia.com>
parent 17528f81
Show whitespace changes
Inline Side-by-side
Showing with 6 additions and 0 deletions
benchmarks/profiler/deploy/profile_sla_moe_dgdr.yaml
View file @ a8213787
...@@ -20,6 +20,12 @@ spec: ...@@ -20,6 +20,12 @@ spec:
# Standard online profiling (not using AI Configurator) # Standard online profiling (not using AI Configurator)
use_ai_configurator: false use_ai_configurator: false
hardware:
# for h200, sweep over 8-16 GPUs per engine
min_num_gpus_per_engine: 8
max_num_gpus_per_engine: 16
num_gpus_per_node: 8
# SLA targets for profiling # SLA targets for profiling
sla: sla:
isl: 3000 # Input sequence length isl: 3000 # Input sequence length
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment