-
```
[2024-09-02 00:39:59,451] [INFO] [real_accelerator.py:203:get_accelerator] Setting ds_accelerator to cuda (auto detect)
[WARNING] Please specify the CUTLASS repo directory as environment varia…
-
[@gavinking] One of the interesting things you can do with a fully-reified type system, that you can't do when type args aren't reified is _instantiate_ a type parameter. For example:
```
Holder crea…
-
### Is there an existing issue for this?
- [X] I have searched the existing issues and checked the recent builds/commits of both this extension and the webui
### What happened?
```
venv "C:\…
-
### Is there an existing issue for this?
- [X] I have searched the existing issues and checked the recent builds/commits
### What happened?
Instead it saves into AppData\Local\Temp\Gradio
### Step…
-
**Is your feature request related to a problem? Please describe.**
So I'm trying to use tritonserver in my project. But it uses a lot of RAM for a single model.
* Is this expected behaviour?
* Ar…
-
venv "C:\Users\vande\stable-diffusion-webui\venv\Scripts\Python.exe"
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug 1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Version: v1.7.0
Commit hash: cf2772fab0a…
-
Given a graph with multiple independent paths between two nodes, topological sort can return multiple solutions.
All these solutions are valid by themselves. However, they can result in different pea…
-
Hi @tomaarsen! Is there a ONNX exporter planned? Have you tried using SpanMarker with ONNX models for inference?
Would be really curious if you experimented with that already! :-)
-
# Current status
`X0Inferer.x0_from_dtheta` requires `MuonBatch.reco_mom` in order to compute X0 during the scattering inversion, however `MuonBatch.reco_mom` simply returns the gen.-level momentum…
-
There are three big problems to overcome in our implementation of fully-reified types:
- performance: dragging around the reified types with instances of any parameterized type is potentially expensiv…