Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

LibreCUDA – Launch CUDA code on Nvidia GPUs without the proprietary runtime

github.com

Post reply on HN
Print view View original

61–70 of 162 posts

Re: LibreCUDA – Launch CUDA code on Nvidia GPUs without the proprietary runtime

#61

Post by shmerl »

SushiHippie wrote: post #56
shmerl wrote: post #8

Since ZLUDA was taken down (by request from AMD of all parties), it would be better to have some ZLUDA replacement as a general purpose way of breaking CUDA lock-in. I.e. something not tied to Nvidia hardware.

> At this point, one more hostile corporation does not make much difference. I plan to rebuild ZLUDA starting from the pre-AMD codebase. Funding for the project is coming along and I hope to be able to share the details in the coming weeks. It will have a different scope and certain features will not come back. I wanted it to be a surprise, but one of those features was support for NVIDIA GameWorks. I got it working…

Ah, that's good. Hopefully it will get back on track then.

Re: LibreCUDA – Launch CUDA code on Nvidia GPUs without the proprietary runtime

#62

Post by candiddevmike »

why_only_15 wrote: post #59
londons_explore wrote: post #50

Earlier quoted context omitted.

The NVidia software stack has the "no use in datacenters" clause. Is this a workaround for that?

Specifically the clause is that you cannot use their consumer cards (e.g. RTX 4090) in datacenters.

That's why we run all of our ML workloads in a distributed GPU cluster located in every employee's house

Re: LibreCUDA – Launch CUDA code on Nvidia GPUs without the proprietary runtime

#65

Post by actionfromafar »

daft_pink wrote: post #39

I think the point of open cuda is to run it on non NVIDIA gpus. Once you have to buy NVIDIA gpus what’s the point. If we had true you competition I think it would be far easier to buy devices with more vram and thus we might be able to run llama 405b someday locally. Once you already bought the NVIDIA cards what’s the point

Yeah like running Linux on a MacBook…

Re: LibreCUDA – Launch CUDA code on Nvidia GPUs without the proprietary runtime

#66

Post by actionfromafar »

cj wrote: post #51
Dalewyn wrote: post #46

Earlier quoted context omitted.

I wonder to what ends trademark protections reach. Firsthand example, both SpaceX and Subaru have services called Starlink. Subaru Starlink was first, but SpaceX Starlink is more famous. I've been confused and I've seen others be confused by the two.

A trademark is scoped to a specific industry / application. Starlink for internet is unlikely to be confused with STARLINK for Subaru car safety systems. (Perhaps the all caps also helps if they were sued) Trademark applications are scoped so that you can’t monopolize a name, you only own the name within the industry you operate in. For example, there’s a real estate investment fund named Apple and even trades with s…

It would make total sense for STARLINK to use satellites to call for help.

Re: LibreCUDA – Launch CUDA code on Nvidia GPUs without the proprietary runtime

#67

Post by amelius »

wackycat wrote: post #13

I have limited experience with CUDA but will this help solve the CUDA/CUDNN dependency version nightmare that comes with running various ML libraries like tensorflow or onnx?

By the way, can anyone explain why libcudnn takes on the order of gigabytes on my harddrive?

Re: LibreCUDA – Launch CUDA code on Nvidia GPUs without the proprietary runtime

#68

Post by Q6T46nT668w6i3m »

daft_pink wrote: post #39

I think the point of open cuda is to run it on non NVIDIA gpus. Once you have to buy NVIDIA gpus what’s the point. If we had true you competition I think it would be far easier to buy devices with more vram and thus we might be able to run llama 405b someday locally. Once you already bought the NVIDIA cards what’s the point

CUDA is ubiquitous in science and an open source alternative to the CUDA runtime is useful, even if the use is limited to verifying expected behavior.

Re: LibreCUDA – Launch CUDA code on Nvidia GPUs without the proprietary runtime

#69

Post by Q6T46nT668w6i3m »

samstave wrote: post #16
heyoni wrote: post #4

Earlier quoted context omitted.

Like anything open source it allows you to know and see exactly what your machine is doing. I don’t want to speculate too much but I remember there being discussions around whether or not nvidia could embed licensing checks and such at the firmware level.

> licensing checks and such at the firmware level. Could you imaging an age where the NVIDIA firmware does LLM/AI/GPU license checking before it does operations on your vectors? (Hello Oracle on SUN e650, My old Friend) ((Worse would be a DRM check against deep-faking or other Globalist WEF Guardrails)) ((oracle had(has) an age olde function where if you bought a license for a single proc and threw it inot a dual pro…

Quadro?

Re: LibreCUDA – Launch CUDA code on Nvidia GPUs without the proprietary runtime

#70

Post by lldb »

amelius wrote: post #67
wackycat wrote: post #13

I have limited experience with CUDA but will this help solve the CUDA/CUDNN dependency version nightmare that comes with running various ML libraries like tensorflow or onnx?

By the way, can anyone explain why libcudnn takes on the order of gigabytes on my harddrive?

Primarily because it has specialized functions for various matrix sizes which are selected at runtime.
Post reply on HN