HackerTrans
TopNewTrendsCommentsPastAskShowJobs

Cieric

486 karmajoined 7 years ago
meet.hn/city/us-Orlando

Socials: - github.com/ookami125

Interests: Gaming, Open Source, Programming

---

Email: [email protected]

Discord: cieric

Kind of do a little bit of everything, but like staying low level if possible.

comments

Cieric
·8 hours ago·discuss
Being fully stopped at a stop light isn't putting my or anyone else's life in danger. If I have a phone in my hand the car is not moving. I also finished the comment before the light turned green so the phone also was no longer in my hand when I needed to start moving.
Cieric
·18 hours ago·discuss
Let me know if you want to hear anything specific about it. It kind of works, so it's not something I recommend doing if it can be avoided, but as Roxxik pointed out there is much room for improvement since this was just a naive just get it to run experiment.
Cieric
·18 hours ago·discuss
On the technical details of mmap I agree (at least while single threaded which is how I believe I'm running it), but making it async does sound like an interesting method for speeding it up. My only goal with my testing was get as large of a model as possible running on a computer that "can't run it." I'm going to have to actually read through the code and figure out how it really works to really make any good optimizations, but as before this was just experiments with using and LLM (claude + codex) to just get it running. Since if they couldn't get it running I'm not sure if I would have wanted to spend time trying to get it working myself.

I also know I did some things that would actually make the perf worse to, like I believe I also had AI mmap the KV Cache to make sure to runs under any circumstance. For actual optimizations based on what I currently know, I'm probably going to try and get the llm running under my igpu on my laptop with persistent shader that has some kind of inbuilt request mechanism. That way the weights that are loaded can be used as fast as possible.

For the expert prediction, I assume I could use the medusa paper as kind of a kick off point for that since I'm already using it to try and predict the next 4 tokens. Doing verification on those 4 tokens is about as much as I can do though since it started to thrash on loading the experts. So some method of predicting even more tokens, but then batching together those with the same experts would probably yield slightly better results in this weird case.

Note: All of my tests have been around programming since that's the use case I'm interested in. I don't actually know if this would preform well in other cases (and anything more broad than that I assume would be slower.)
Cieric
·yesterday·discuss
Yeah I'll see what I can transfer over from my llama.cpp work. As before I'm not too experienced with llm work, but I have a lot of experiments I'm trying out. So I'll make a PR if I get any interesting results.
Cieric
·yesterday·discuss
I was actually just working on the same thing as this, but I went down the route of mmapping the entire model into memory to avoid the extra ram usage. I also had Claude implement Medusa[1] on the model to try and avoid loading an additional model into memory but still get the benefits of MTP. Currently at a stop light so I can't list everything and I didn't get to read your full post either yet.

To expand since I just got home, I'm making all of my modifications to llama.cpp, the goal was to eventually put this on a SBC of some kind with an nvme to handle the mmapped files. I think the theoretical limit of my current setup is about 1.8 tok/s based on prior testing but that is also with the additional medusa heads not fully trained (I honestly don't know if the counting it's generated tokens or not.)

In the end it seems like the idea we had is similar, I just don't know how to write an llm parser/runner from scratch yet and instead of specifying what needed to stay in memory I just let the linux kernel handle it.

Oh last note, I also capped llama.cpp usage to 16GB of my 32GB, so it might be possible to get it down even lower.

[1] https://arxiv.org/abs/2401.10774
Cieric
·last month·discuss
I think I can understand that reasoning. I do have a tendency to explore, especially at the start since it gives me a view of what the site can already do, cause I wouldn't want to run into issues with my own projects without knowing of the possible limitations ahead of time.

If anything since the keyboard shortcut already exists, you could always put it in little cursor menu at the bottom of the screen. But yeah up to you, I look forward to your progress.
Cieric
·last month·discuss
Seems interesting an I'll take more of a peek after work, but one thing that stood out to me is the only way back to the home page after navigating to a repo is the back button. Going back to the home page via the back button also doesn't retain that "new" was selected. But I agree with others, I do like the simplicity of the site.
Cieric
·last month·discuss
I can't say I know how they actually did it, but taking a look at the trailer I can point out that it looks like the spaces are confined and your character is on rails. I'm mainly going off of the instant direction changes that don't appear to be 45 degrees off from the camera direction. Once it's constrained down to a single line/path you could do some wild things like cube mapping a video, where the position in the video is tied to the characters position. I can't say I know how they would take that video though, my best guess there is the scenes are constructed in 3d software, just it was to expensive for real time rendering.
Cieric
·2 months ago·discuss
I actually do this whenever I add a youtube channel, but some shorts still sneak through. Just as a warning to whoever tries it themselves.
Cieric
·2 months ago·discuss
All good, and agreed the fork author is in the wrong here. I just like keeping the facts straight since that can inform better arguments and discussions.
Cieric
·2 months ago·discuss
An example give by donho is "SomeProject : a macOS port of Notepad++" so it seems like the name can be used which will make it appear in searches. It just has to be clearly something else.
Cieric
·2 months ago·discuss
The only place I see that is from a user "LiEnby" not "aletik", and none of aletik's existing messages are edited. All replies I see with the message are also to LiEnby. I don't agree with aletik's slow response in any way, but I don't think your claim is correct either. Do you have anything to prove that this was said by aletik?
Cieric
·5 months ago·discuss
Neither did I, feel free to email me or message me on discord and I can try to download the video and send it to you.
Cieric
·5 months ago·discuss
Here is a video that I actually just watched recently on that exact thing.

https://youtu.be/jfLAaGtNc7U
Cieric
·5 months ago·discuss
I've been interested in doing something similar in the past, but I could really never solve issues like domain squatting and stopping individuals from claiming every name possible. Do you have a place where you keep these plans or have discussions around it? Or even just a place where I could get updates if anything does come of it?
Cieric
·5 months ago·discuss
As someone from the US I would suggest viewing both as adversarial. I don't really trust my own government, but if I was born abroad I would trust them even less.
Cieric
·5 months ago·discuss
He's avoiding LLVM which is a compiler framework. Not LLMs as has been stated a few times in the comments already.
Cieric
·5 months ago·discuss
I don't have a lot of faith there, but that's mainly due to my experience being correcting peoples assumption that all gpus waves are 32 lanes. I might be biased there specifically since it's my job to fix those issues though.
Cieric
·5 months ago·discuss
Now that I could agree with, the only place where hiccups have started to occur are with wave intrinsics where you can share data between thread in a wave without halting execution. I'm not sure disallowing it would be the best idea as it cuts out possible optimizations, but outright allowing it without the user knowing the number of lanes can cause it's own problems. My job is the fun time of fixing issues in other peoples code related to all of this. I have no stakes in rust though, I'd rather write a custom spirv compiler.
Cieric
·5 months ago·discuss
I'm not even sure a 32 wide array would be good either since on AMD warps are 64 wide. I wouldn't go fully towards auto vectorization with though.