-
For example: https://github.com/intel/intel-xpu-backend-for-triton/actions/runs/10950266371/job/30405179010
The log is too big it is almost impossible to see the compilation / testing results in a …
-
### 🚀 The feature, motivation and pitch
I have tried a few times to add Unified Memory support to Pytorch, so as to leverage as many resources of my computer as possible while running training and in…
-
### System Info
```Shell
accelerate >= 0.32.0
```
### Information
- [ ] The official example scripts
- [ ] My own modified scripts
### Tasks
- [ ] One of the scripts in the examples/ folder of A…
-
Tried to load and distribute model to devices in a layerwise way, by using deepspeed zero3 context manager as below:
```python
with ds.zero.Init(config_dict_or_path=deepspeed):
model …
-
### System Info
```Shell
- `Accelerate` version: 0.35.0.dev0
- Platform: Linux-5.15.0-121-generic-x86_64-with-glibc2.35
- `accelerate` bash location: redacted
- Python version: 3.10.14
- Numpy…
-
### Error Description
I am encountering the error, `Native API returns: -30 (PI_ERROR_INVALID_VALUE)`, when trying to run llama.cpp with the latest IPEX-LLM, following the official quickstart guide o…
-
Hi, OS: windows 10, Arc A750
Driver: 5081
请问chatglm3和Baichuan2-7B随着对话次数增加，内存不停增大。用这个KV cache demo也不能解决：
demo link: https://github.com/intel-analytics/BigDL/blob/main/python/llm/portable-zip/chat.py…
-
Hello everyone, I am starting to test some systems with the [nvidia gds](https://docs.nvidia.com/gpudirect-storage/overview-guide/index.html) technology enabled. This [github repository](https://githu…
-
### 🐛 Describe the bug
Skip the model in pre-ci. Please retrieve the case, if triton gets fixing.
https://github.com/intel/intel-xpu-backend-for-triton/issues/1353
### Versions
Latest main.
-
用户通知