This commit is contained in:
@@ -0,0 +1,25 @@
|
||||
apiVersion: lumbridge/v1
|
||||
kind: Scene
|
||||
metadata:
|
||||
name: qwen38-dflash-mem
|
||||
version: 1
|
||||
description: "MEASUREMENT ONLY — DFlash2 with a 75 GB static pool, voice-vox dropped to pay for it."
|
||||
author: karti
|
||||
tags: [experimental, benchmark, dflash]
|
||||
|
||||
# NOT A PRODUCTION SCENE. It exists to answer one question: does DFlash2 beat
|
||||
# EAGLE when it is given something closer to the memory MiaAI-Lab's profile
|
||||
# assumes (0.90 / ~110 GB)? At 0.46 it did not (22.4 vs EAGLE 22.8 tok/s,
|
||||
# acceptance 0.17-0.25 vs 0.46-0.68).
|
||||
#
|
||||
# voice-vox (20 GB) is dropped purely to afford the bigger pool. Do not leave
|
||||
# this scene active — go back to `qwen38` when the measurement is done.
|
||||
models:
|
||||
- brain-qwen38-dflash-mem
|
||||
- ears
|
||||
- voice
|
||||
|
||||
budget_gb: 100
|
||||
activation:
|
||||
order: listed
|
||||
wait_healthy: true
|
||||
Reference in New Issue
Block a user