-
Over the last week(s) there's been quite some discussion about binary caches.
This issue is meant to give an overview of discussions, and previous & current problems, and a suggested way forward.
…
-
## Problem
What happens when service worker gateway is used to load website which has own service worker code?
IIUC if the scope of the new service worker is the same as or a subset of the scope…
lidel updated
2 months ago
-
Currently, the profile criterion is a little bit off. Predicted time does not correspond to the real value (the car drives using the trajectory faster than the estimated time). It could be a problem o…
-
### 🚀 The feature, motivation and pitch
We see 14% perf win on timm models with layout optimization. But enabling dynamic shape cause 6% perf drop instead.
Theoretically we should also see wins wi…
-
```
Reported by project member thomaschneider, Today (moments ago)
Requested feature:
TASTY could provide a tool that allows to read in circuits in one format,
potentially apply different optimizatio…
-
**Describe the bug**
One of my teammates said he followed this page: https://onnxruntime.ai/docs/performance/graph-optimizations.html to generate an offline model. It says:
```
All optimizations …
-
Matt and I chatted offline about #166 and potential traps when implementing ``set_index``.
Generally, we shouldn't use ``divisions`` while simplifying the Expression tree and pushing stuff up and …
-
This issue would like to raise 3 main points derived from my brief experience toying around with the compiler:
- I feel that optimization features should be off by default. Choosing to apply optimi…
-
Does vLLM support 8 bit quantization? We need to use vLLM with large context window (>1K tokens). We tried AWQ but the generation quality is not good. Any pointer will be greatly appreciated.
-
I am a student who greatly admires your research. Packetgame is very interesting research in my opinion!
I currently have research interests similar to yours and am working on designing a system simi…