-
### Search before asking
- [X] I have searched the YOLOv8 [issues](https://github.com/ultralytics/ultralytics/issues) and [discussions](https://github.com/ultralytics/ultralytics/discussions) and fou…
-
### Proposal to improve performance
Hi, how to test tensorrt-llm serving correctly? I've tested on llama2-8b-chat and llama3-8b and the performances are too bad for TTFT. Could you tell me where go…
-
### 🐛 Describe the bug
I might as well flag this, although I think the fix is just a case of implementing a symbolic override for aten::_index_put_impl correctly. Here's a test case:
```
import t…
-
### 🐛 Describe the bug
Running
```
PYTORCH_ALL_SAMPLES=1 python test/inductor/test_torchinductor_opinfo.py -k test_comprehensive_clamp_max_cpu_bool
```
results in
```
Command:
/home/isuruf/.…
-
### Solution to issue cannot be found in the documentation.
- [X] I checked the documentation.
### Issue
## Steps to reproduce
1. Install the latest JAX and Keras versions with GPU support from …
-
### 🐛 Describe the bug
Crash with large batch size during backwards pass on CUDA.
```
# bug report -- with cuda (but not CPU), this crashes at large batch sizes
#
# torch version: 2.4.0a0+f70b…
-
### 🐛 Describe the bug
According to this https://pytorch.org/docs/main/notes/get_start_xpu.html
When I make triton with USE_XPU=1, I encountered the following error
```
Building wheels for col…
-
### Before You Report a Bug, Please Confirm You Have Done The Following...
- [X] I have updated to the latest version of the packages.
- [X] I have searched for both [existing issues](https://github.…
gafap updated
3 months ago
-
### 🐛 Describe the bug
DEBUG builds on aarch64 have been failing since this patch by @malfet : https://github.com/pytorch/pytorch/pull/124023
Specifically this line that was added:
```cpp
…
-
I'm on Ubuntu 22.04, Anaconda environment, with the following versions:
```
neo4j 5.23.0
neo4j-runway 0.8.1
graphviz …