AI without the smoke and mirrors

Release notes.
For a physical AI lab.

Hardware changes, model changes, networking changes, failures, benchmark deltas, and conclusions—tracked like software releases instead of buried in blog posts.

magicthellm / changelog
LAB 0.4.1

changed
+ second 24 GB GPU
+ tensor split
+ airflow revision

measured
first-token latency
tokens / second
power draw
thermals

verdict
keep the change
01 / Current Log

Experiments, not announcements.

Every entry should make the lab more reproducible. If the hardware, runtime, model, or benchmark method changes, the release notes should say exactly what changed.

0.3

Architecture defined

The project was organized around models, memory, compute, networking, agents, and security.

0.2

24 GB baseline

Planned baseline for inexpensive datacenter GPU inference, cooling, power, and model fit.

0.1

100GbE test

Find the first workload where faster Ethernet produces a measurable AI-lab advantage.

02 / Format Demo

One experiment.
Documented the same way every time.

This is the reusable release-note format. The point is not decoration. It forces each test to state the hypothesis, configuration, method, result, verdict, and next step.

VersionLAB 0.4.1
StatusCompleted
Hardware2 × 24 GB GPUs
Model70B class / Q4
lab-0.4.1.md
# hypothesis
A second 24 GB GPU makes
70B Q4 inference practical
without heavy CPU offload.

# configuration
2 × 24 GB GPU
128 GB system RAM
70B Q4 model
same prompt + context

# method
1. record baseline
2. add second GPU
3. hold workload constant
4. measure latency + tok/s
5. record power

# result
model fit     PASS
throughput    +31%
power         +46%
noise         regrettable

# verdict
Useful if acquisition cost is low.

# next
compare with one newer GPU
03 / Required Data

What every release should record.

A result without configuration is almost useless. These are the pieces that make the lab notes worth returning to later.

HW

Hardware state

Server, CPU, RAM, GPU, PCIe placement, storage, network, cooling, and power.

SW

Software state

OS, driver, runtime, model, quantization, context, flags, and relevant versions.

MET

Measured result

Load time, first-token latency, tokens/sec, utilization, watts, thermals, and failures.

04 / Release Stream

How the lab evolves.

Small versioned changes make it obvious which variable moved and whether the change survived testing.

LAB 0.4.2

Tensor split revised

Changed model distribution across two GPUs and re-ran the same prompt and context.

LAB 0.4.3

Cooling redesign

Added directed airflow and measured sustained throughput, thermals, and noise again.

LAB 0.5.0

Second compute node + 100GbE

Introduced a second host and tested when the network becomes part of the AI compute path.

05 / Release Philosophy
“If the configuration changed, the benchmark changed.”

The release notes are the technical memory of the lab: what changed, what worked, what failed, and what should be tested next.