-
## Problem
- Model publishers may not always assign the right Model Architecture tags
- We want to detect when a model is a [TensorRT Engine](https://github.com/triton-inference-server/tensorrtllm_b…
-
command: `ruff check test.py`
ruff version: `ruff 0.0.282`
settings: `select = ['ALL']`
example:
```python
import polars as pl
pldf = pl.DataFrame()
pldf.pivot() # PD010 `.pivot_table`…
-
gomlx seems to call deprecated XLA Client APIs (e.g. https://github.com/gomlx/gomlx/blob/main/c/gomlx/computation.cpp#L743), but it should be using new PjRT ones.
Lots of those API calls seem auto…
-
This task, should you choose to accept it, is to really show your stuff by adding some features
to Imp. What kind of constructions are you used to having in languages you have programmed in
that Imp…
-
We have already enabled TEST01 for SDXL - wasn't mandatory for v4.0 (because the proposal came late), but mandatory for v4.1. https://github.com/mlcommons/inference/pull/1574
NVIDIA has checked int…
-
**Describe the bug**
Can't open inference server.
**To Reproduce**
1. Run install_env.bat with USE_MIRROR=false and INSTALL_TYPE=stable
2. Change API_FLAGS.txt and enable "--infer", then Run sta…
-
In version 1.5 i was able to bypass Dex using extension provider.
I added it to the istio configmap:
```
extensionProviders:
- name: "dex-auth-provider"
envoyExtAuthzHttp:
…
-
During my experience with the REACH output from the last Big Run, I collected several of the cases where the inference was wrong. Please use them for debugging/improving the inference rules. Those err…
-
### System Info
GPU: A100
Python:3.10.13
### Information
- [ ] Docker
- [ ] The CLI directly
### Tasks
- [ ] An officially supported command
- [ ] My own modifications
### Reproduction
`cargo …
-
All existing inference rules should have test cases exercising them.