-
Hi,
I noticed that `fortio` reports lots of read errors when benchmarking a project of mine. Since I couldn't find the cause in my code, I double checked using `curl` and `wrk`. Both tools work fin…
-
Both tool participants and outsiders such as industry partners can propose benchmarks. All benchmarks must be in .onnx format and use .vnnlib specifications, as was done last year. Each benchmark must…
-
### Feature request
TGI provides some valuable metrics on model performance and load today. However, there are still a number of missing metrics, the absence of which poses a challenge for orchestr…
-
I think that what limits PeerTube adoption is that instances are perfect for personal/organization use but not to build a free service like YouTube where everyone can upload videos without limits. The…
-
Hi there 👋 I'm looking to add another Scala GraphQL library to the benchmarks. When I first looked at the current results I was a bit surprised that Sangria (Scala) was performing this badly. After lo…
-
Now that we can load GPTQ files that haven't been quantized by TGI's quantization script, I thought I'd do a set of tests to see which formats work and which don't. I'm using https://huggingface.co/Th…
-
Hi! Thanks a lot for this gem! It's working beautifully.
I'm using it in a Docker container in Kubernetes. If multiple jobs are processed at the same time (Sidekiq worker with N threads), does the …
-
### System Info
Running on a DGX-A100 server with the provided docker image, with the unrelated modifications in #272.
### Information
- [x] Docker
- [ ] The CLI directly
### Tasks
- […
-
I don't see the config files for nginx; but from the look of the results, it seems that it was configured as a reversed-proxy; so you'll only see the extra overhead here.
In order to see the benefi…
vtt updated
10 months ago
-
The test with YugabyteDB 2.9.0 performs about _300 times slower than Postgres_ :( both with rf=1 and 1 master/tablet and rf=3 and 3 masters/tablets and with rf=1, one master and 3 tablet servers.
I…