Smokeydope

I think i've discovered something important in the field I dabble in as a advanced hobbyist. Like this was a breakthrough and perspective shift enough for me to stay awake all night into the morning until I had to go to sleep testing it works and boilerplating the abstract paper. I constructed a theoretical framework, practical implementation, and statistically analyzed experimental results across numerous test cases. I then put my findings into as good a technical paper as I could write up. I did as much research as I could to make sure nobody else had written about this before.

At this point though I don't really know how to proceed. Im an outsider systems engineer not an academic, and arXiv requires you be endorsed/recognized as a member of the scientific community with like a college email or written recommendation by someone already known. Then whenever I look at the papers on arxiv they always look a very specific way I cant get with libreoffice writer. Theres apparently a whole bunch of rules on formatting and font and style and this and that. Its overwhelming and kind of scary.

So. What do i do here? I have something I think is important enough to get off my ass and get in touch with a local college to maybe get a recommendation. I'd like to have my name in the community and contribute.

I think i've discovered something important in the field I dabble in as a advanced hobbyist. Like this was a breakthrough and perspective shift enough for me to stay awake all night into the morning until I had to go to sleep testing it works and boilerplating the abstract paper. I constructed a theoretical framework, practical implementation, and statistically analyzed experimental results across numerous test cases. I then put my findings into as good a technical paper as I could write up. I did as much research as I could to make sure nobody else had written about this before.

At this point though I don't really know how to proceed. Im an outsider systems engineer not an academic, and arXiv requires you be endorsed/recognized as a member of the scientific community with like a college email or written recommendation by someone already known. Then whenever I look at the papers on arxiv they always look a very specific way I cant get with libreoffice writer. Theres apparently a whole bunch of rules on formatting and font and style and this and that. Its overwhelming and kind of scary.

So. What do i do here? I have something I think is important enough to get off my ass and get in touch with a local college to maybe get a recommendation. I'd like to have my name in the community and contribute.

Please help! I'm trying to remove this metal plate to get to my GPU for cleaning. From what I saw it had one star pattern bolt at the end of a slope connecting to the chassis, removing it loosened it a little but I don't know how to proceed. Dont want to damage anything.

Edit: I got it figured out! Had to pull a metal tab on the back as I jostled/slid the plate. Thank you!

Recently I've been experimenting with Claude and feeling the burn on the premium API usage. I wanted to know how much cheaper my local llm was in terms of cost-per-token output.

Claude Sonnet is a good reference with 15$ per 1 million tokens out, so I wanted to know comparatively how many tokens 15$ worth electricity powering my rig would generate.

(These calculations are just simple raw token generation by the way, in real world theres cost in initial hardware, ongoing maintenance as parts fail, and human time to setup thats much harder to factor into the equation)

So how does one even calculate such a thing? Well, you need to know

1. how many watts your inference rig consumes at load
2. how many tokens on average it can generate per second while inferencing (with context relatively filled up, we want conservative estimates)
3. cost of electric you pay on the utility bill in kilowatts-per-hour

Once you have those constants you can extrapolate how many kilowatt-hours worth of runtime 15$ in electric buys then figure out the total amount of tokens you would expect to generate over that time given the TPS.

The numbers shown in the screenshot are for a fully loaded into vram model on the ol' 1070ti 8gb. But even with partially offloaded numbers for 22-32b models at 1-3tps its still a better deal overall.

I plan to offer the calculator as a tool on my site and release it under a permissive license like gpl if anyone is interested.

Theres a lot more to this stuff than I thought there would be when starting out. I spent the day familiarizing with how to take apart my pc and swap gpus .Trying to piece everything together.

Apparently in order for PC to startup right it needs a graphical driver. I thought the existance of a HDMI port on the motherboard implied the existance of onboard graphics but apparently only special CPUs have that capability. My ryzen 5 2600 doesnt. The p100 Tesla does not have graphical display capabilities. So ive hit a snag where the PC isnt starting up due to not finding a graphical interface output.

I'm going to try to run multiple GPU cards together on pcie. Hope I can mix amd Rx 580 and nvidia tesla on same board fingers crossed please work.

My motherboard thankfully supports 4x4x4x4 pcie x16 bifurcation which isa very lucky break I didnt know going into this 🙏

Strangely other configs for splitting 16x lanes like 8x8 or 8x4x4 arent in my bios for some reason? So I'm planning to get a 4x bifurcstion board and plug both cards in and hope that the amd one is recognized!

According to one source The performance loss for using 4x lanes for GPUs doing the compute i m doing is 10-15 % surprisingly tolerable actually.

I never really had to think about how pcie lanes work or how to allocate them properly before.

For now I'm using two power supplies one built into the desktop and the new 850e corsair psu. I choose this one as it should work with 2-3 GPUs while being in my price range.

Also the new 12v-2x6 port supports like 600w enough for the tesla and comes with a dual pcie split which was required for the power cable adapter for Tesla. so it all worked out nicely for a clean wire solution.

Sadly I fucked up a little. The pcie release press plastic thing on the motherboard was brittle and I fat thumbed it too hard while having problems removing the GPU initially so it snapped off. I dont know if that's something fixable. It doesnt seem to affect the security of the connection too bad fortunately. I intend to grt a pcie riser extensions cable so there won't be much force on the now slightly loosened pcieconnection. Ill have the gpu and bifurcation board layed out nicely on the homelab table while testing, get them mounted somewhere nicely once I get it all working.

I need to figure out a external GPU mount system. I see people use server racks or nut and bolt meta chassis. I could get a thin plate of copper the size of the desktops glass window as a base/heatsink?

Theres a lot more to this stuff than I thought there would be when starting out. I spent the day familiarizing with how to take apart my pc and swap gpus .Trying to piece everything together.

Apparently in order for PC to startup right it needs a graphical driver. I thought the existance of a HDMI port on the motherboard implied the existance of onboard graphics but apparently only special CPUs have that capability. My ryzen 5 2600 doesnt. The p100 Tesla does not have graphical display capabilities. So ive hit a snag where the PC isnt starting up due to not finding a graphical interface output.

I'm going to try to run multiple GPU cards together on pcie. Hope I can mix amd Rx 580 and nvidia tesla on same board fingers crossed please work.

My motherboard thankfully supports 4x4x4x4 pcie x16 bifurcation which isa very lucky break I didnt know going into this 🙏

Strangely other configs for splitting 16x lanes like 8x8 or 8x4x4 arent in my bios for some reason? So I'm planning to get a 4x bifurcstion board and plug both cards in and hope that the amd one is recognized!

According to one source The performance loss for using 4x lanes for GPUs doing the compute i m doing is 10-15 % surprisingly tolerable actually.

I never really had to think about how pcie lanes work or how to allocate them properly before.

For now I'm using two power supplies one built into the desktop and the new 850e corsair psu. I choose this one as it should work with 2-3 GPUs while being in my price range.

Also the new 12v-2x6 port supports like 600w enough for the tesla and comes with a dual pcie split which was required for the power cable adapter for Tesla. so it all worked out nicely for a clean wire solution.

Sadly I fucked up a little. The pcie release press plastic thing on the motherboard was brittle and I fat thumbed it too hard while having problems removing the GPU initially so it snapped off. I dont know if that's something fixable. It doesnt seem to affect the security of the connection too bad fortunately. I intend to grt a pcie riser extensions cable so there won't be much force on the now slightly loosened pcieconnection. Ill have the gpu and bifurcation board layed out nicely on the homelab table while testing, get them mounted somewhere nicely once I get it all working.

I need to figure out a external GPU mount system. I see people use server racks or nut and bolt meta chassis. I could get a thin plate of copper the size of the desktops glass window as a base/heatsink?

I now do some work with computers that involves making graphics cards do computational work on a headless server. The computational work it does has nothing to do with graphics.

The name is more for consumers based off the most common use for graphics cards and why they were first made in the 90s but now they're used for all sorts of computational workloads. So what are some more fitting names for the part?

I now think of them as 'computation engines' analagous to a old car engine. Its where the computational horsepower is really generated. But how would ram make sense in this analogy?

Bonus:

Previous tip:

I got the ti helix tip sunset color to finally complete my H2. Wow is this thing a huge improvent in several ways. Airflow is greatly increased which I immediately noticed. The m+ tip was restrictive comparatively.

The speed to heat with induction heater is faster fue to lower thermal mass of titanium and the helix being machined to be the lightest weight wise. This means the tip allows for more efficient use of energy for more heat cycles per battery charge.

I like the helical twisty swirlies. The color was purple not reddish orange so I was surprised and thought they sent the wrong thing! It seems any amount of finger oil turns it from light purple to sunset tan orange. I think that's bitching I love color changing stuff and purple is my favorite color so I was happy regardless.

The holes didnt have noticsble burrs thats what I was worried about. It was machined to within my expectations, ran it through some ultrasonic alcohol anyways before use as is good practice.

This is one of my favorite finds. I believe its a gold plated half of some kind of locket or pendant.

Dont get discouraged because you aren't pulling precious metals and valuable loot out of the ground most of the time. The chance is always there. Keep at it!