-
From what Deepti told us this morning, it is possible to make a reservation for ~50 nodes on CloudLab, provided the machines are small (64gb of RAM).
Her suggestion on how to provision such a cluster…
-
The [Shared Memory Multithreading for Dart](https://github.com/dart-lang/language/blob/main/working/333%20-%20shared%20memory%20multithreading/proposal.md) proposal outlines a number of modifications …
-
Something I have noticed over the past 4 years or so of using Dolphin Memory Engine is that the memory detection it has is relatively unstable and likes to fail on occasion. I imagine this is due to t…
-
I just noticed, that fine tuning FLUX with the command in the README (dataset image size 512,512, batch size 1) will result in 8GB of shared memory
![image](https://github.com/user-attachments/asse…
-
# Summary
OP-TEE OS is crashing when performing a warm reset of the processor.
# Details
## Build
The build is branched off of https://github.com/OP-TEE/optee_os/commit/31bb491f8e7c78794b6…
-
### Problem Description
https://github.com/ggerganov/llama.cpp/discussions/9960#discussioncomment-11141805
https://github.com/ggerganov/llama.cpp/issues/9964
### Operating System
Windows…
-
Hello, is there a way to make a shared library built with Memory sanitizer that is importable from Python ? I tried with Pybind11 and I am getting either undefined symbols on the import or if I link l…
VA-GS updated
1 month ago
-
# 🐞 Describe the Bug
Facing an `OutOfResources` error with 64 fine-grained experts and dropless MoE enabled, even though there is sufficient GPU memory.
# 🔄 Steps to Reproduce
Steps to reprod…
-
### What happened?
When forcing llama.cpp to use "GPU + CUDA + VRAM + shared memory (UMA)", we noticed:
- High CPU load (even when only GPU should be used)
- Worse performance than using "CPU + RAM…
-
On the PR https://github.com/ros2/rclcpp/pull/2624 I provide a fix to allow the user to make copies of loaned messages, keeping them beyond the subscription callback scope. With the fix, the loaned me…