-
闲来无事想试试P100的推理速度
在装载模型的时候出现错误:
```
(…)kura-14b-qwen2beta-v0.9-iq4_xs_ver2.gguf: 100%
7.85G/7.85G [00:39
-
`*** Error completing request
*** Arguments: ('task(zwfjlvs2uko8hna)', , 'hyperdetailed photography, minimalist art sculpture, metallic sculpture, product photograph, desktop wallpaper,', '', [], 20…
-
### Description
The iteration variable becomes NaN at initialization and the solver tries to solve with NaN. This leads to continuous error and warning in the log file.
The models are listed below…
-
Hi :)
i run successfully the transformers version, but i have difficulties with the diffusers version,
i changed the "assets/concept_list.json" according my data, but i got the next error
why?
…
-
Hey Dan,
I ran into the same initial problem as charlesincharge (the tmux session encapsulation obscuring output while debugging `python run_lfadsqueue.py`) . As you suggested, I tried running the…
-
In this issue you can either:
- **Add papers** that you think are interesting to read and discuss (please stick to the format).
- **vote**: should be done using :+1: on comments
-
I meet this issue while using ollama on MTL iGPU
![image](https://github.com/intel-analytics/ipex-llm/assets/92354341/b9cc7b61-3b61-4615-b1f2-40a85ac22aee)
my IPEX-LLM version as below
![image](htt…
-
# 🐛 Bug
I am currently experimenting with different scaled dot product attention implementations to evaluate training speed and GPU memory consumption.
I compared all methods running the followi…
-
Nikhil Garg, Londa Schiebinger, Dan Jurafsky and James Zou’s follow-on article, 2017. [“Word Embeddings Quantify 100 Years of Gender and Ethnic Stereotypes.”](https://www.pnas.org/content/115/16/E3635…
-
**Describe the bug**
I was using deepspeed zero3 in a compression script. When the model was instantiated, I found that every module was injected with a post_init method, which partitioned the parame…