Smokeydope

joined 2 years ago
MODERATOR OF
 
[–] [email protected] 0 points 4 days ago (3 children)

What does an MCP server do?

0
Homelab upgrade WIP (lemmy.world)
submitted 4 days ago* (last edited 4 days ago) by [email protected] to c/[email protected]
 

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.

I'm going to try to run multiple cards together. 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. Strangely not 8x8 or 8x4x4 for some reason? So I'm planning to get a 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. I choose this one as it should work with 2-3 GPUs while being in my price range. Also the new 12v-2x6 port supportd like 600w and comes with a dual pcie split which was required for the 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. Ill have the gpu and bifurcation board layed out nicely on the homelab table while testing.

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?

0
Homelab upgrade WIP (lemmy.world)
submitted 4 days ago* (last edited 4 days ago) by [email protected] to c/[email protected]
 

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?

[–] [email protected] 0 points 5 days ago (1 children)
[–] [email protected] 6 points 5 days ago* (last edited 5 days ago)

The point in time after the first qbit based supercomputers transitioned from theoretical abstraction to physical proven reality. Thus opening up the can-of-worms of feasabily cracking classical cryptographic encryptions like an egg within human acceptable time frames instead of longer-than-the-universes-lifespan timeframes.. Thanks, superposition probability based parallel computations.

[–] [email protected] 0 points 5 days ago* (last edited 5 days ago) (1 children)

Thank you for deciding to engage with our community here! You're in good company.

Kobold just released a bunch of tools for quant making you may want to check out.

Kcpp_tools

I have not made my own quants. I usually just find whatever imatrix gguf bartowlski or the other top makers on HF release.

I too am in the process of upgrading my homelab and opening up my model engine as a semi public service. The biggest performance gains ive found are using CUDA and loading everything in vram. So far just been working with my old nvidia 1070ti 8gb card.

Havent tried vllm engine just kobold. I hear good things about vllm it will be something to look into sometime. I'm happy and comfortable with my model engine system as it got everything setup just the way I want is but I'm always open to performance optimization.

If you havent already try running vllm with its CPU nicencess set to highest priority. If vllm can use flash attention try that too.

I'm just enough of a computer nerd to get the gist of technical things and set everything up software/networking side. Bought a domain name, set up a web server and hardened it. Kobolds webui didnt come with https SSL/TLS cert handling so I needed to get a reverse proxy working to get the connection properly encrypted.

I am really passionate about this even though so much of the technical nitty gritty under the hood behind models goes over my head. I was inspired enough to buy a p100 Tesla 16gb and try shoving it into an old gaming desktop which is my current homelab project. I dont have a lot of money so this was months of saving for the used server class GPU and the PSU to run it + the 1070ti 8gb I have later.

The PC/server building hardware side scares me but I'm working on it. I'm not used to swapping parts out at all. when I tried to build my own PC a decade ago it didnt last long before something blew so there's a bit of residual trauma there. I'm worried about things not fit right in the case, or destroying something or the the card not working and it all.

Those are unhealthy worries when I'm trying to apply myself to this cutting edge stuff. I'm really trying to work past that anxiety and just try my best to install the stupid GPU. I figure if I fail I fail thats life it will be a learning experience either way.

I want to document the upgrade process journey on my new self hosted site. I also want to open my kobold service to public use by fellow hobbyist. I'm not quite confident in sharing my domain on the public web though just yet I'm still cooking.

[–] [email protected] 4 points 6 days ago

Coincidentally the same name as my geometry themed experimental grunge rock band

[–] [email protected] 17 points 6 days ago* (last edited 6 days ago)

The first thought I had was this same scenario but all grown up. Imagine two fully grown 700 lb bovines crammed in your kitchen staring down your dishes lol theyre all cute until they become living flesh tanks then they're still cute but hella bulky and slightly intimidating

[–] [email protected] 0 points 6 days ago* (last edited 6 days ago)

nods and continues to use original doom wads with the red cross design for health pickups because the green one from BFG editions look like shit

[–] [email protected] 3 points 6 days ago* (last edited 6 days ago)

Being an alternate protocol nerd is a trip. Most people have no clue what a gopher/Gemini/spartan/finger is or how they differ from the web. The few handful on this planet that do are just other nerds who like to blogspam tech nerd things. It would be nice if the web enshittified so much even the average non techie was put into a position to look into these alternatives.

[–] [email protected] 0 points 6 days ago

Right now THCA mail-order is under fire from goons in house and senate so if your gonna order on bulk legally may want to do it soon the lawmaking could go either way. I recommend eight horse hemp for cheap mid bulk and wnc-cbd for the top shelf premium

 

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?

[–] [email protected] 0 points 1 week ago* (last edited 1 week ago)

Have you by chance checked out kobold.cpp lite webUI? It allows some of what your asking for like RAG for worldbuilding, adding images for the llm to describe to add into the story, easy editing of input and output, lots of customization in settings. I have a public instance of kobold webui setup on my website and I'm cool with allowing fellow hobbyist using my compute to experiment with things. If your interested in trying it out to see if its more what youre looking for, feel free to send me a pm and I'll send you the address and a api key/password.

[–] [email protected] 0 points 1 week ago* (last edited 1 week ago) (2 children)

In an ideal work what exactly would you want an AI integrated text editor to do? Depending on what you need to have happen in your workflow you can automate copy pasting and automatic output logging with python scripts and your engines api.

Editing and audiing stories isnt that much different from auditing codebases. It all boils down to the understanding and correct use of language to convey abstraction. I bet tweaking some agebic personalities and goals in vscode+roo could get you somewhere

 

It seems mistral finally released their own version of a small 3.1 2503 with CoT reasoning pattern embedding. Before this the best CoT finetune of Small was DeepHermes with deepseeks r1 distill patterns. According to the technical report, mistral baked their own reasoning patterns for this one so its not just another deepseek distill finetune.

HuggingFace

Blog

Magistral technical research academic paper

 

WOAH

 

So, ive never really used RAG before. I kept hearing about it and understood it in concept, so wanted to play around with it. I play a table top map drawing game called DELVE that has lots of rules to keep track of requiring lots of manual page flips on my slow ereader.

I wanted to see of it was possible to teach my local model about DELVE through my engines basic RAG system that works by providing a big text file and doing some keyword searches in it based off user input. The engine pulls in local chunks of text document around important keywords as context. This is different than more complex and sophisticated versions of RAG that work off fancy vector space math or something like that. Whatever, kobold is my engine of choice and I'm happy to have something that half works and is simple enough to grasp.

So the first step was converting the game manual PDF to text file. I did this using calibres ebook-convert tool. Then I looked through and tried to clean some glaring issues up invdvitably theres gonna be jank converting PDF unicode or tables.

sudo apt install calibre

ebook-convert delve.pdf delve.txt

Once its cleaned up a little I threw it in kobold lites context>textdb tab and enabled it.

Its cool how such a simple process manages to let the model leverage local datasets. I was shocked when it correctly recited proper game rules.

Full Input/Output shown in screenshotInput: How to play delve?

Output:

Okay, I need to figure out how to explain how to play DELVE based on the provided info snippets. Let's start by breaking down the key components mentioned.

First, the materials required are pencil, eraser, grid paper or blank paper, notepad for resources and trade goods, a deck of standard playing cards without jokers initially, and tokens for various purposes like dwarves, enemies, etc. The starting setup involves drawing a stairwell at the top center as the entrance. Resources (hearts ♥) and Trade Goods (diamonds ♦) start at 20 each. Then there's mention of Soldiers being placed at the entrance. Jokers are removed from the deck at first but added later at depth 5.

The turn structure seems to involve the following steps: prepare, explore, retreat. Each turn has phases like exploring, checking threats, downtime. There's talk about expanding the hold by adding rooms, handling threats through combat or avoidance, managing resources and trade goods.

The Bloodrunes are optional challenges that offer boons but also transport to a nightmare layer upon choosing them. Each rune has specific effects. For example, the Rune of Nightmares immediately starts the player in a nightmare layer with rewards for defeating ancient monsters.

There's a part about using cards instead of dice. Drawing suits corresponds to D4 results, while colors correspond to D2. That's important because the game uses these rolls frequently.

Rooms have various functions. Smelters let you convert ore into metal, Armories provide soldiers, Quarries generate stone, etc. Each room has costs and benefits. Some advanced rooms like Deep Delve or Burglar Alarms have special abilities.

Threats include monsters, thieves, and other events. Combat uses Strength and Defense with armor effects. Thieves steal half your trade goods unless you have burglar alarms. Monsters can cause damage or drain resources.

Trade is done by visiting the Marketplace on certain turns where you exchange goods. The Marketplace deck has different cards affecting trade values. You can sell excess goods or buy needed items at varying rates.

Ancient Ones are powerful enemies encountered as you delve deeper. They have high stats and unique abilities. Beating them gives significant rewards but poses risks if not prepared.

Endgame conditions involve reaching depth 10, accumulating wealth, or being overrun by threats. If you win, you get to set up a new hold with better starting conditions.

I need to structure this explanation step-by-step, covering setup, turn phases, actions in each phase, room building, handling threats, trading, and endgame conditions. Also mention the Bloodrunes as optional challenges with their own rules. Highlight how card draws replace dice rolls for D4 and D2. Maybe note that grid paper isn't mandatory, but it helps visualize the hold layout.

How to Play DELVE: Step-by-Step Guide

  1. Setup

    Materials Needed:
    Pencil/eraser, grid/notebook paper, notebook (for tracking resources), standard playing cards (Jokers removed initially), tokens (coins, dice, etc.).
    Start Your Hold:
    Draw a central stairwell on the top row of grid paper as the entrance.
    Resources:
    Begin with 20 Resources (♥) and 20 Trade Goods (♦) in your notebook. Add 5 Soldiers (tokenized) at the entrance.

  2. Deck & Game Layers

    Remove Jokers from the deck. At Depth 5, re-add them for "Legendary Finds."
    Use cards instead of dice:
    Roll 1D4: Suit = ♠=1, ♣=2, ♦=3, ♥=4.
    Roll 1D2: Color = Black=1, Red=2.

  3. Turn Structure

    Prepare Phase:

     Spend resources to build rooms (e.g., Smelter, Armory) or upgrade defenses.  
     Manage soldiers and prepare for threats.  
    

    Explore Phase:

     Draw two cards from the deck: choose one to reveal a room, threat, or resource.  
     Build rooms by placing them on grid paper (cost varies by type).  
    

    Retreat Phase:

     Resolve combat, theft, or other threats. Sold-out rooms generate income (e.g., Quarry → Stone).  
    
  4. Optional Challenges: Bloodrunes

    Place a Bloodrune (e.g., "Rune of Nightmares") on the first row before starting. Each rune triggers immediate effects (e.g., starting in a nightmare layer) but offers boons like combat bonuses.

  5. Rooms & Upgrades

    Basic Rooms:
    Smelter (3♥): Convert ore to metal.
    Armory (5♥): Add soldiers (1 per turn).
    Quarry (2♥): Gather stone.
    Advanced Rooms:
    Deep Delve (10♥): Explore deeper layers faster.
    Burglar Alarms (7♥): Mitigate thief losses.

  6. Threats

    Combat: Roll strength vs. enemy defense (armor reduces damage). Soldiers protect rooms.
    Thieves: Steal half your Trade Goods unless you have Burglar Alarms.
    Ancient Ones: Powerful bosses at deeper levels (e.g., "The Devourer") with unique abilities and high rewards.

  7. Trading & Marketplace

    Visit the Marketplace every 3 turns by drawing cards: adjust supply/demand for resources. Sell excess goods or buy needed items at fluctuating rates.

  8. Victory Conditions

Win by reaching Depth 10, accumulating 200+ Trade Goods, or surviving until the deck runs out. Lose if overrun by threats, depleted of resources, or defeated in combat.

  1. Bloodrune Example: Rune of Nightmares

    Start immediately on a nightmare layer without access to the Marketplace. Defeat ancient monsters for powerful rewards but risk doom.

Tips:

Use grid paper to visualize your hold’s layout.  
Balance room upgrades with threat mitigation.  
Bloodrunes add difficulty but enhance replayability.  

Enjoy delving into the depths! 🌋⚔️🗡️

 

Come on bro just swipe the credit card

 

Die motherfucker steel motherfucking steel fool, die motherfucking steel motherfucking steel

Also sorry to all the real weebs out there who felt a minor anyeurism at reading this up-down left-to-right instead of manga right-left as Nihei intended. I made the meme for westerners in mind.

 

I have a memory foam matress on top a cot. Every now and then I need to sun dry the mattress and cot from a decent amount of moisture trapped between the two. Is there a way to keep the moisture out or even just reduce it?

 

YSK because webpages are increasingly bloated from excessive trackers, popups, sidebars, and more. This diminishes the experience of reading, eats up your precious internet data, and threatens your privacy.

Newswaffle is a public service created by Acidus that intelligently strips webpages of their cruft and leaves only the valuable text content. Its based in gemtext and was originally intended to be accessed using the gemini protocol, however it can very easily be reformated to HTML and proxied through HTTP for normal web browser usage. The proxy I am using is SmolNet Portal by Mozz.

Newswaffle Homepage (proxied)

If you have a kobo e-ink ereader or similar device with extremely simple web browser its invaluable for getting a modern webpage to render correctly.

Source Code

YSK because the people who made these tools and host them on their own time and dime, may not be around forever. Only a few other people on this planet know these tools exist or actively use them. There are only one public instance of these services running thanks to the makers themselves. Ideally we need some self hosters to deploy and fork these tools to ensure they exist in the future. That can't happen if nobody knows about them.

Newswaffle github

SmolNet Portal Proxy github

 
view more: next ›