coolingcube-tp 0.1.0

Tensor Parallel feasibility analyser — should you use TP, how many GPUs, does DFlash break scaling?

coolingcube-tp

Tensor Parallel feasibility analyser. Answers the question every multi-GPU inference user has:

Should I use TP? How many GPUs? Does DFlash break scaling?

Install

pip install coolingcube-tp

Usage

# RTX5090 + RTX PRO 6000, 32B model, DFlash enabled
coolingcube-tp --gpus rtx5090 rtx_pro_6000 --model 32 --dflash 8

# 4x RTX4090, 70B model, no DFlash
coolingcube-tp --gpus rtx4090 rtx4090 rtx4090 rtx4090 --model 70

# List all supported GPUs
coolingcube-tp --list-gpus

Python API

from coolingcube_tp import analyse_tp

result = analyse_tp(
    gpus=["rtx5090", "rtx_pro_6000"],
    model_params_b=32,
    dflash_draft=8,
    interconnect="pcie"
)

print(result["verdict"])
print(result["recommendation"])

How it works

NFF-IMC (Non-Feasible Finite — Inverse Mass Control) applied to inference TP:

• Computes per-GPU compute time from real TFLOPS and bandwidth specs
• Models AllReduce communication overhead per layer
• Applies DFlash draft amplification when enabled
• Returns speedup vs single GPU and a clear verdict

Free. No API calls. Runs locally.

coolingcube.cc