Files
exo/.github/configs/bench_simple.yaml
2025-11-11 18:03:39 +00:00

116 lines
3.0 KiB
YAML

# Simple single-shot benchmark
# Tests 2 instances concurrently on 2 nodes
# Hardware configuration - maps runner labels to instance counts
hardware_plan:
puffin4: 1
puffin8: 1
# Environment variables to set on each node
environment:
PLACEHOLDER: "placeholder"
# OVERRIDE_MEMORY_MB: 50000
MLX_METAL_FAST_SYNCH: 1
# Timeout for instance and runner readiness (seconds)
timeout_seconds: 1800
# Model instances to run concurrently
model_ids:
# - "mlx-community/DeepSeek-V3.1-8bit"
# - "mlx-community/Kimi-K2-Instruct-4bit"
- "mlx-community/Kimi-K2-Thinking"
# - "mlx-community/Qwen3-235B-A22B-4bit"
# - "mlx-community/Llama-3.3-70B-Instruct-4bit"
# - "mlx-community/Llama-3.3-70B-Instruct-8bit"
# - "mlx-community/Llama-3.2-1B-Instruct-4bit"
# Sharding strategy: "Pipeline" or "Tensor"
sharding: "Pipeline"
# Instance type: "MlxRing" or "MlxIbv"
instance_meta: "MlxIbv"
# If true, run requests sequentially (no overlap); if false, fire-and-forget (default: false)
no_overlap: true
# Benchmark stages
# pp: 64, 256, 1024, 2048, 4096, 8192, 16384
# g: 64, 512
stages:
# - name: "simple"
# prompt_length: 512
# generation_length: 10
# time_between_requests: 2.0
# iterations: 5
- name: "pp64_g64"
prompt_length: 64
generation_length: 64
time_between_requests: 2.0
iterations: 5
# - name: "pp64_g512"
# prompt_length: 64
# generation_length: 512
# time_between_requests: 2.0
# iterations: 10
- name: "pp256_g64"
prompt_length: 256
generation_length: 64
time_between_requests: 2.0
iterations: 5
# - name: "pp256_g512"
# prompt_length: 256
# generation_length: 512
# time_between_requests: 2.0
# iterations: 10
- name: "pp1024_g64"
prompt_length: 1024
generation_length: 64
time_between_requests: 2.0
iterations: 5
# - name: "pp1024_g512"
# prompt_length: 1024
# generation_length: 512
# time_between_requests: 2.0
# iterations: 10
- name: "pp2048_g64"
prompt_length: 2048
generation_length: 64
time_between_requests: 2.0
iterations: 5
# - name: "pp2048_g512"
# prompt_length: 2048
# generation_length: 512
# time_between_requests: 2.0
# iterations: 10
- name: "pp4096_g64"
prompt_length: 4096
generation_length: 64
time_between_requests: 2.0
iterations: 5
# - name: "pp4096_g512"
# prompt_length: 4096
# generation_length: 512
# time_between_requests: 2.0
# iterations: 10
- name: "pp8192_g64"
prompt_length: 8192
generation_length: 64
time_between_requests: 2.0
iterations: 5
# - name: "pp8192_g512"
# prompt_length: 8192
# generation_length: 512
# time_between_requests: 2.0
# iterations: 10
# - name: "pp16384_g64"
# prompt_length: 16384
# generation_length: 64
# time_between_requests: 2.0
# iterations: 10
# - name: "pp16384_g512"
# prompt_length: 16384
# generation_length: 512
# time_between_requests: 2.0
# iterations: 10