-
## Environment
**TensorRT Version**: 10.1
**NVIDIA GPU**:3060
**CUDA Version**:11.1
## Steps To Reproduce
/trtexec --onnx=./lk_800.onnx --saveEngine=./lk_bf16.trt --bf16 --profilingVerbos…
-
#### Your system information
* System information from steam (`Steam` -> `Help` -> `System Information`) in a [gist](https://gist.github.com/): ryzen 5 5600, 32gb ram, rx580, ssd sata, debian stabl…
-
These have been kept "as-is", with an explicit reference to load (and average load).
They should be re-worked in the more general context of "work".
Related to #167 and #121 but specialized to the…
-
### Proposal to improve performance
_No response_
### Report of performance regression
I have a single machine 8xH100 SXM system. I wanted to see how vLLM (0.5.5) compares to other engines with TP=…
-
## Issue report
Hello,
We're having a strange behaviour in our passenger servers. Each almost two hours every day the load average of the machine increase a lot during ~10m and then go stable ag…
-
### log:
12/04 16:06:52 - mmengine - INFO - Evaluating bbox...
Loading and preparing results...
DONE (t=0.01s)
creating index...
index created!
Running per image evaluation...
Evaluate annotati…
-
## Objective
Baseline observability to support the effort [here](https://www.notion.so/buildwithgrove/Permissionless-Demand-Load-Testing-24feefb2f34f4399a941beb374bb6ea1) and the development efforts …
-
### Checklist
- [X] I've looked through [the documentation](https://clementtsang.github.io/bottom/nightly/) and [existing open issues](https://github.com/ClementTsang/bottom/issues?q=is%3Aopen+is%3A…
-
### Describe the issue
The tensor output results of the same ONNX model with the same inputs vary depending on whether optimizations are enabled or disabled. The issue specifically involves the Pad F…
-
**Is your feature request related to a problem? Please describe.**
I have noticed Azure Load Testing Reports have the ability to report metrics in 90, 95 and 99 percentile but does not have the optio…