😁
I'm still playing Mudrunner. Is there a big difference?
I mean I don’t really see the point here.
There isn't one. I guess I should have made that more clear. Sorry. 🫤
And I’m not sure if I’m missing something ...
Nope, just a guy with too much time on his hands. I mean, I hope someone out there found it a little informative. There are a lot of people thinking "If Ollama doesn't work then I'm out of luck." I'm just trying to let people know there are other options.
Yes, the Nvidia cards get 30+ t/s together or individually, but the point of this was to see if AMD and Nvidia could work together. Now that this works, I might actually buy an AMD GPU.
No, I didn't change my drivers at all. I figured it would probably work with older drivers. But then the problem is my 4060 won't work with anything older than 545(I think).
I do have another PC I could put the 770 in. That might be worth trying.
It just kills me to have these old cards sitting around doing nothing. The 770 was kind of a beast in its time. But that's life.
I guess I could donate them to some Peertuber who does retro videos or something.
A few pics of them in their heyday (ok, they were already past their prime at the time)
I gotta speak up in her defense. It's kind of easy to mishear lyrics. Just like in my favorite Pearl Jam song "I love Amstel Lite"
So much better than when I might have said something dumb and I'm staring at that unread message notification.
I’ve read you can force the new Vulkan Driver on it with some kernel flags.
Not gonna lie, that sounds beyond my scope. Once I got llama.cpp compiled, everything just worked. I would have no idea how to troubleshoot anything.
I saw a video where someone got the new Indiana Jones running on a Vega 64, so there's really no telling what's possible on AMD hardware. They put so much effort into designing chips, but so little into supporting them.
My laptop (RX 7600s) gets more tokens/sec in Vulkan than in ROCm. I don't know what that's all about.
it’s illegal.
I'm sure that'll stop him.
I hate Trump (really I do), but I can't argue with this. Inflation happens; stamping out a piece of copper alloy has lots of fixed costs. We used to have a half cent coin. Things change.
The real question should be "why do they have to print so many pennies every year?" Paper bills last an average of 18 months before they need to be replaced, but coins don't typically wear out. Where are these pennies going?
I agree with CameronDev, not so much on the capacity, but the bandwidth. At 100+ Gb, the Ryzen/Core platforms are really holding you back with their weak I/O.
If you need that much memory, you might be better off picking up a used Xeon/Epyc from Ebay. Their CPU speeds are lower, but the quad channel RAM could make up for it, depending on what you're trying to do.
Thanks. I was confused at first, wondering why there was no picture of their console on the website.
Classic episode; one of my favorite
I followed a tutorial and trained my first LoRA today. I was surprised to see it was using both my GPUs - 1080ti and 3060, but then it failed halfway through. I won't print the whole log, but here are the important parts that caught my attention:
More than one GPU was found, enabling multi-GPU training.
2023-09-17 10:35:32.654285: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
Blocksparse is not available: the current GPU does not expose Tensor cores
[E ProcessGroupNCCL.cpp:455] Some NCCL operations have failed or timed out. Due to the asynchronous nature of CUDA kernels, subsequent GPU operations might run on corrupted/incomplete data.
[E ProcessGroupNCCL.cpp:460] To avoid data inconsistency, we are taking the entire process down.
So my guess is the tensor errors are because of the GTX card which doesn't have tensor cores. I removed that card and everything ran fine with just the 3060. I imagine either card would work by itself, but the differences between the two may have been enough to cause data corruption.
So I'm wondering if anyone has this working with multiple RTX cards. Can it work across generations - 3060 and 4060ti, etc. Or does it have to be the same generation? Thanks in advance.
As for the LoRA itself, it needs more work (denim boots)
