-
It would be extremely helpful for the framework submitters to understand the performance of their submissions, especially where the bottlenecks are when running in the target environment. For this pur…
-
### Description
Profiling a customer's app, I see time spent in:
```
87.65ms (1.2%) 15.49ns (
-
### Describe the bug
On multiple GPU systems, using HIP or CUDA, a process is spawned on all GPUs instead being spawned only on one of them. (See To reproduce section)
This result in memory leak…
-
**Describe the bug**
We have an ingestion job, running periodically in Kubernetes, it runs fine with DataHub 0.12.x versions.
You can see the memory stays stable under 1GiB during the executio…
-
Image resizing and profiling (I know what I mean)
-
We've long been investigate lag spikes caused by Starstorm 2's Wayfarer TP boss since its release last October. The difficulty issue was the dev team could not reproduce it, but we implemented a bunch…
Hevia updated
3 weeks ago
-
你好,在使用yolov8中,我在将best.onnx通过/usr/src/tensorrt/bin/trtexec --onnx=best_640.onnx --saveEngine=best_640.trt --buildOnly --minShapes=images:1x3x640x640 --optShapes=images:2x3x640x640 --maxShapes=image…
-
Hello, i'am trying to install milvus on a k8s cluster using helm:
```
helm install milvus milvus/milvus --values='/home/siradjedd/airstream/application/k8s/helm/milvus/values/milvus.yml' --names…
-
### How would you like to use vllm
I want to run Phi-3-vision with VLLM to support parallel calls with high throughput. In my setup (openai compatible 0.5.4 VLLM server on HuggingFace Inference End…
-
Hi there, when I try to attach RenderDoc for graphics profiling I get a error leading to a crash when calling rprContextCreateMesh() with return code -18.
The code works fine when RenderDoc is not …