-
### Your current environment
...
### How would you like to use vllm
I have downloaded a model. Now on my 4 GPU instance I attempt to quantize it using AutoAWQ.
Whenever I run the script below I ge…
-
If you look at page 36, the enable signal for the tri-state drivers in block "FF47 BGP" is ``!(CPU_RD2 && FF47)``, so they must be active when enable is low. Same goes for the tri-state driver ``HOPE`…
-
### Describe the bug
Hi.
Here, I am trying to do inpaint using **realisticStockPhoto** with **SDXL_FILM_PHOTOGRAPHY_STYLE** LoRA.
```
device = "cuda"
model_path = "realisticStockPhoto_v20.saf…
-
## Feature Request
Add performance monitoring support to Talos.
### Description
It would be great to have a performance monitoring tool (such as `perf`, see https://www.brendangregg.com/perf.…
-
After reading the [Ballooning](https://github.com/firecracker-microvm/firecracker/blob/main/docs/ballooning.md) documentation my understanding of the `deflate_on_oom` is that if the parameter is set t…
-
The code:
```
from decord import VideoReader, cpu, gpu
class DecordInit(object):
"""Using Decord(https://github.com/dmlc/decord) to initialize the video_reader."""
def __init__(self, …
-
This is exactly what I'm looking for to extend my existing cluster that is high cpu/RAM AND 0 GPU.
Can you give some insight if the workers can run on low cpu/ram systems, such as a series of rpi 5 wi…
-
Hi,
I tried to train an agent performing a custom RL task, but I found that the performances and behaviors of the agent are different, depending on the training device (CPU or GPU).
In general, …
-
**What would you like to be added**:
We would like to propose a new feature in Kueue that enables dynamic scaling of job parallelism and resource allocation (CPU, RAM, and pods) based on job backlo…
-
## Background
Encode complexity settings are hardcoded for WebRTC's built-in encoders (libvpx VP8/VP9, libaom AV1 and OpenH264). The settings depend on platform, number of CPU cores and video resol…