LibreCuda
By mikex86
Juice-Labs
Juice Community Version Public Release (by Juice-Labs)
| LibreCuda | Juice-Labs | |
|---|---|---|
| 2 | 21 | |
| 1,028 | 525 | |
| 1.3% | 0.0% | |
| 8.5 | 8.7 | |
| 4 months ago | about 1 year ago | |
| C | Go | |
| MIT License | MIT License |
The number of mentions indicates the total number of mentions that we've tracked plus the number of user suggested alternatives.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
LibreCuda
Posts with mentions or reviews of LibreCuda.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2024-08-09.
-
Show HN: Attaching to a Virtual GPU over TCP
sorry, I didn't mean nvapi, I meant rmapi.
I bet you saw this https://github.com/mikex86/LibreCuda
they implemented the cuda driver by calling into rmapi.
My understanding is if there is a remote rmapi, other user mode drivers should work out of the box?
- LibreCUDA – launch CUDA code on Nvidia GPUs without the proprietary CUDA runtime
Juice-Labs
Posts with mentions or reviews of Juice-Labs.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2024-08-09.
-
Show HN: Attaching to a Virtual GPU over TCP
There is a GPU-over-network software called Juice [1]. I've used it on AWS for running CPU-intensive workloads that also happen to need some GPU without needing to use a huge GPU instance. I was able to use a small GPU instance, which had just 4 CPU cores, and stream its GPU to one with 128 CPU cores.
I found Juice to work decently for graphical applications too (e.g., games, CAD software). Latency was about what you'd expect for video encode + decode + network: 5-20ms on a LAN if I recall correctly.
[1] - https://github.com/Juice-Labs/Juice-Labs
- GPU-over-IP for LLM inference?
- GTA 5 running in Qemu without PCI Passthrough using Juicy Labs
-
This looks very cool: GPU-over-IP with Juice. You can attach GPU to non GPU nodes, share GPU across multiple users and applications, bring GPU to your data (vs bringing your data to the GPU) - all with just software.
The website https://www.juicelabs.co/ they have an community version as well https://github.com/Juice-Labs/Juice-Labs
-
EGPU ALTERNATIVE?
I recently discovered juicelabs.co but I have not yet tested it. Maybe worth a look.
-
Why I think 3D artists should get an eGPU for rendering, even if they have a desktop [How stuff works + Idea]
Or you could even use a remote GPU like Juice GPU
-
Using Cloud-GPU as an eGPU?
check out https://www.juicelabs.co/
-
Looking for a Bitfusion replacement? I think I may have found something really cool... Juice - which not only supports CUDA but all the graphical APIs
So our lab had been using Bitfusion until recently for a large number of VM deployments. With Bitfusion support coming to an end, we were talking about solutions and did some Googleing around GPU-over-IP and stumbled across these guys: www.juicelabs.co
-
is it possible to install Automatic1111 and manage it like locally, but using a shared gpu service such as runpod.io/endpoints?
The Juice may help passing gpu over IP, I haven't tried it yet though
-
ClosedAI strikes again
Even then you can always use Juice. https://www.juicelabs.co/
What are some alternatives?
When comparing LibreCuda and Juice-Labs you can also consider the following projects:
qCUDA - qCUDA: GPGPU Virtualization at a New API Remoting Method with Para-virtualization
ffmpeg-over-ip - Connect to remote ffmpeg servers
model_analyzer - Triton Model Analyzer is a CLI tool to help with better understanding of the compute and memory requirements of the Triton Inference Server models.
ZLUDA - CUDA on non-NVIDIA GPUs