35 lines
1.1 KiB
YAML
35 lines
1.1 KiB
YAML
apiVersion: lumbridge/v1
|
|
kind: Scene
|
|
metadata:
|
|
name: qwen38-dspark
|
|
version: 1
|
|
description: "qwen38-mia tuning with the DSpark speculative stack (code/tool-call optimised)."
|
|
author: karti
|
|
tags: [brain, vision, voice, sglang, dspark, benchmark]
|
|
|
|
# Same model set and same MiaAI-Lab tuning as `qwen38-mia`; only the
|
|
# speculative stack differs (EAGLE/MTP -> DSpark) plus torch.compile and
|
|
# continuous-decode-steps 2.
|
|
#
|
|
# Benchmark with MiaAI-Lab's own net-decode harness, NOT the prose `performance`
|
|
# suite: python3 /tmp/ndec_ours.py
|
|
# qwen38-mia (EAGLE) baseline: code 31.60 / prose 23.97 tok/s
|
|
# MiaAI-Lab reports for DSpark: code 51.5 / prose 18.3
|
|
#
|
|
# DSpark is faster on code/math/tool-calls and SLOWER on free-form prose, so
|
|
# check both probes before adopting — the squawk/news path is prose.
|
|
#
|
|
# Same swap discipline as every other scene: kill stale `scene activate`,
|
|
# deactivate, wait for free -g >= 110 GB, activate, then activate again to
|
|
# persist desired.
|
|
models:
|
|
- brain-qwen38-dspark
|
|
- ears
|
|
- voice-vox
|
|
- voice
|
|
|
|
budget_gb: 100
|
|
activation:
|
|
order: listed
|
|
wait_healthy: true
|