Written by: J1N, Techub News
Introduction: Epoch One to Two
Kuzco is a network dedicated to LLM large language model computing power mining. This year, it was selected for the Crypto Startup Accelerator (CSX) Fall Accelerator Program launched by a16z in New York on September 9. Projects selected by the program will receive at least $500,000 in investment from a16z and will receive guidance and support from the a16z operations team. The accelerator program has now ended.
On November 16, Kuzco announced that the first phase (Epoch One) incentive plan will end on November 18, 2024, all operations will be suspended, data snapshots will be permanently stored, and the final points ranking will be announced on the new leaderboard.
According to official disclosure, Epoch One was launched on March 6, 2024, with a peak number of more than 8,000 devices. The network runs the 8B-specification Llama-3 AI large language model released by Meta , with a total inference of more than 1 trillion tokens.
It also announced that financing information and project development roadmap will be released in the next few weeks, and the second phase (Epoch Two) incentive plan will start on December 9. Epoch Two will bring some new features, such as higher throughput and reliability of NVIDIA hardware; encourage users to access top computing devices such as A100 and H100; support more image generation and multimodal language model VLM.
There is still half a month of preparation time before the opening of Epoch Two. This article will discuss:
Share the practice and achievements of personal mining, and the transition from stand-alone to cluster.
Demonstrate the whole process of obtaining financing through research and practice, and building a high-specification machine.
Discuss the compatibility of hardware configuration with project requirements and answer common questions from investors.
Epoch One Review: Single Soldier Combat
Configuration
My configuration list includes RTX series graphics cards 2060, 2070S, 3080, 4060, 4060Ti, 4 4070S and 2 Apple M2 and M3 devices. These devices are distributed on several hosts, laptops and a dedicated mining machine.
cost
It is worth mentioning that these graphics cards were originally purchased by the author every year according to game needs, not specifically for mining. Therefore, the hardware purchase cost is not included in the cost calculation, only the actual electricity cost of the mining machine is counted. Here is an example of the mining machine assembled in the first article " a16z "disciple" Kuzco's practical guide: How to efficiently perform AI computing power mining? "
The mining machine configuration:
Motherboard: z490 (will be replaced with industrial board later)
CPU: 10th Gen I9
Graphics card: 2060, 2070s, 3080, 4060ti, 4070s
Hand rubbing machine
The following figure shows the amount of electricity consumed by the mining machine in October and November, a total of 564 degrees, and the points (KZO Points) obtained are about 600 million points. All machines add up to about 1.1 billion points. The specific electricity cost needs to be calculated based on the electricity cost of each location, and this is only for reference.
On the far right of the picture, a total of 1 billion points were obtained
Preparing for Epoch Two: Cluster Deployment
Based on what I shared in the first article and my rich experience in operation and maintenance from personally participating in equipment assembly, debugging, and environmental deployment, I successfully obtained a certain amount of financial support and invested all of it in assembling high-performance mining machines to further improve computing power and operational efficiency.
From single soldier to cluster deployment
Configuration and selection logic for high-specification machines
Based on the author's practical experience in Epoch One, the motherboard, CPU, graphics card, power supply, platform and network configuration were fully optimized, and a more suitable hardware combination was selected, which not only improved the overall stability, security and efficiency of operation, but also paid more attention to the liquidity of the second-hand market in hardware selection. This strategy can effectively reduce the actual investment cost and provide subsequent participants with a more cost-effective option.
Motherboard
The author chose an industrial motherboard instead of the mainstream B85, mainly based on a comprehensive consideration of performance, stability and cost-effectiveness.
In terms of performance, running Kuzco's Llama-3 model requires starting multiple Docker processes. Running these processes in parallel will take up a lot of CPU resources and require high CPU performance, but the CPU compatible with B85 cannot meet this requirement.
In addition, industrial motherboards have obvious advantages in long-term stable operation, high temperature resistance and manufacturer warranty. They also have stronger liquidity in the second-hand market, so they are undoubtedly the best choice.
Graphics
The author chose to use 4070S as the main graphics card, mainly based on the following points:
Advantages of AI computing performance: Compared with the 30 series graphics cards, the 40 series graphics cards have a much greater performance improvement in AI computing than in gaming performance. The core reason is that AI computing power mainly depends on the number of CUDA cores of the graphics card, and the 40 series graphics cards have significantly more CUDA cores than the 30 series graphics cards.
Energy efficiency advantage : The author conducted detailed tests on multiple GPUs and calculated the average power consumption of each token.
4060Ti (160W): 0.125 Tokens/W
3080 (330W): 0.22 Tokens/W
4090 (450W): 0.26 Tokens/W
4070S (220W): 0.38 Tokens/W
Judging from the test results, the 4070S performs best in terms of the balance between performance and power consumption. Its higher energy efficiency directly reduces electricity costs, making it the most cost-effective choice.
Price and liquidity in the second-hand market: As a mid-to-high-end graphics card, the 4070S has high liquidity and value retention in the second-hand market, further reducing the cost of holding the device while providing flexibility for subsequent hardware upgrades.
CPU
As mentioned above, Kuzco's Llama-3 needs to start multiple Dockers when running, which significantly occupies CPU resources, especially when running with multiple GPUs, the CPU occupancy rate may be as high as 80%-90%. Therefore, multi-core and multi-threaded processing capabilities are particularly important. A high-performance, multi-threaded, and stable CPU can not only effectively support multi-tasking operations, but also ensure the stability and efficiency of the entire mining process.
The 13th generation i5 can reach 70%+ occupancy when fully loaded with graphics cards
Network environment
The soft router is the square box in the picture
The network environment is also crucial in mining. Even if a high-performance graphics card is configured, if the network is not optimized, the computing power will be seriously affected. According to the author's actual measurement, insufficient network speed may cause the computing power to drop to 30%, and low-quality network nodes may directly lead to the inability to connect to the Kuzco network. Both of these are unacceptable for mining. In order to solve these problems, the author adopts a soft routing solution, which is not only easy to configure, but also can run efficiently without human intervention after the setup is completed. In theory, it can also support the access of unlimited devices. As for the specific operation method, it is recommended that readers consult relevant information according to their needs.
power supply
Classic Great Wall 2000w Nuclear Power Supply
When choosing a power supply, you need to pay special attention to the peak power consumption, which is why even though the rated power consumption of 7 4070S is only 1540W, I still choose to use dual 2000W power supplies, with a total power of 4000W. This is not a waste of resources, but out of consideration for the stability and safety of equipment operation.
The graphics card will have peak power consumption during operation, that is, at certain moments its actual power consumption may reach 1.5 times or even more of the rated power consumption, and then fall back to normal levels. If the power supply is not enough to cope with this peak, it may trigger the forced shutdown mechanism of the power supply, or even cause damage to the graphics card. This is a fatal threat to the normal operation of the mining machine.
4070s operating power consumption performance
Take 4070S as an example. Although its rated power consumption is 220W, its peak power consumption may exceed 400W. The peak power consumption of 7 graphics cards may reach more than 3000W in total, so dual 2000W power supplies are configured to ensure stable operation of the machine. Users who configure multiple 4090s should pay special attention to the fact that the rated power consumption of a single 4090 is 450W, while the peak power consumption may be as high as 770W. In the case of multiple cards, two power supplies alone may not be able to meet the needs. At this time, three power supplies are usually required to ensure system stability.
4090 operating power consumption performance
Replenish
As for BIOS settings, hardware compatibility, and remote management, I will not elaborate on these issues here. There are a lot of free tutorials on the Internet for reference, and most problems can be solved by following the tutorials. It is recommended to conduct targeted research and processing based on your own hardware configuration and needs, which is simple and efficient.
Risks and Benefits
Answering the most concerned question: How much money can be mined every day? Frankly speaking, there is no clear answer to this question, because risks and benefits always coexist. I can share a clear point of view: whether it is the cryptocurrency circle or the traditional industry, if any project can accurately calculate the daily income, then you may not make a lot of money if you enter. Unless you have some monopoly resources, such as extremely low electricity costs or very cheap mining equipment, you can have an advantage in income. However, not everyone has such resources.
The author chooses equipment with good liquidity in order to reduce investment risks and cost pressure. Taking Kuzco mining as an example, the cost is mainly concentrated on the depreciation of hardware and electricity costs, so your maximum loss is limited to these fixed costs. If you do not participate under the premise of low cost, then any investment decision loses its meaning. It should be emphasized that the characteristics of mining the first mine determine that there is no clear profit expectation, but this is also the potential of the first mine.
From a subjective point of view, this track has a huge market prospect: on the one hand, Kuzco has received investment support from a16z; on the other hand, the demand for LLM large language models is rapidly expanding. Think about it, almost no one will not use LLM, right? Platforms like OpenAI's ChatGPT, Meta's Llama, and Musk's XAI, which have received high rounds of financing, clearly show the growth potential of this industry.
For ordinary people, it is not easy to directly participate in the AI industry. On the one hand, the threshold of AI technology is high; on the other hand, the training of AI models requires a huge amount of resources and funds, and most people cannot afford such costs. By joining the AI computing power network through Kuzco, ordinary people can easily participate in this high-growth field under the premise of controllable costs, contribute to AI computing power, and gain benefits at the same time.
In addition, the price of Bitcoin is about to break through $100,000. There is a huge risk of retracement behind the rise from $16,000 in 2022 to the current high point. If you choose to directly purchase the tokens of AI projects, you will also face similar high volatility risks. In contrast, participating in the AI computing network is a more robust option: not only is the cost clearly controllable, but it can also cut into the high-growth track of the AI industry with relatively low risks. This is one of the practical ways for ordinary people to enter the field of AI in the current environment.
