-
**Environment:**
- OS: Linux
- GPU and driver version: NVIDIA, Driver Version: 535.183.01. Vulkan Instance Version: 1.3.283
- SDK or header version if building from repo: 2d73636d5
- Options …
-
Small LLMs trained using FP8 with 32 GPUs can achieve 20~30% speed up comparing with bf16.
However, scaling up to 1000+ GPUs only achieve less than 5% speed up (TP2 PP4 VP4).
Any suggestion to de…
-
With privacy concerns these days in mind could we consider please making TLS the default for site visits to hackage.haskell.org by a redirect from http -> https?
-
aim is to make everyones life easier to experiment with AI
## requirements & deliverables
- create python script to setup a VM in VAST.AI (all automated)
- easy install (integrated with the s…
-
### What is the bug?
If I enter something in the search field a message pops up and shows no results:
 working with Wasmtime. My original motivation for doing this was that XNNPACK has been used as a benchmark t…
-
From the source code(roi_pooling_cuda.c) and my naive experiments, it seems that the RoI pooling layer only support batch size equals to one. Does anyone know why?